diff --git a/.gitignore b/.gitignore
index 94b0107c8..9ac8c6f4c 100644
--- a/.gitignore
+++ b/.gitignore
@@ -5,3 +5,6 @@ saved_models/weights.best.from_scratch.hdf5
 saved_models/weights.best.vgg16.hdf5
 .ipynb_checkpoints/
 bottleneck_features/DogVGG16Data.npz
+*.h5
+*.tflite
+
diff --git a/.idea/.gitignore b/.idea/.gitignore
new file mode 100644
index 000000000..13566b81b
--- /dev/null
+++ b/.idea/.gitignore
@@ -0,0 +1,8 @@
+# Default ignored files
+/shelf/
+/workspace.xml
+# Editor-based HTTP Client requests
+/httpRequests/
+# Datasource local storage ignored files
+/dataSources/
+/dataSources.local.xml
diff --git a/.idea/dog-project.iml b/.idea/dog-project.iml
new file mode 100644
index 000000000..04f073d9f
--- /dev/null
+++ b/.idea/dog-project.iml
@@ -0,0 +1,13 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$">
+      <excludeFolder url="file://$MODULE_DIR$/venv" />
+      <excludeFolder url="file://$MODULE_DIR$/__MACOSX/lfw" />
+      <excludeFolder url="file://$MODULE_DIR$/dogImages" />
+      <excludeFolder url="file://$MODULE_DIR$/lfw" />
+    </content>
+    <orderEntry type="jdk" jdkName="Python 3.8 (dog-project) (2)" jdkType="Python SDK" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>
\ No newline at end of file
diff --git a/.idea/inspectionProfiles/profiles_settings.xml b/.idea/inspectionProfiles/profiles_settings.xml
new file mode 100644
index 000000000..105ce2da2
--- /dev/null
+++ b/.idea/inspectionProfiles/profiles_settings.xml
@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>
\ No newline at end of file
diff --git a/.idea/misc.xml b/.idea/misc.xml
new file mode 100644
index 000000000..557ea96df
--- /dev/null
+++ b/.idea/misc.xml
@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.8 (dog-project) (2)" project-jdk-type="Python SDK" />
+</project>
\ No newline at end of file
diff --git a/.idea/modules.xml b/.idea/modules.xml
new file mode 100644
index 000000000..501649b81
--- /dev/null
+++ b/.idea/modules.xml
@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/dog-project.iml" filepath="$PROJECT_DIR$/.idea/dog-project.iml" />
+    </modules>
+  </component>
+</project>
\ No newline at end of file
diff --git a/.idea/vcs.xml b/.idea/vcs.xml
new file mode 100644
index 000000000..94a25f7f4
--- /dev/null
+++ b/.idea/vcs.xml
@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="$PROJECT_DIR$" vcs="Git" />
+  </component>
+</project>
\ No newline at end of file
diff --git a/AccVal_acc.png b/AccVal_acc.png
new file mode 100644
index 000000000..6b3a7e96f
Binary files /dev/null and b/AccVal_acc.png differ
diff --git a/LossVal_loss.png b/LossVal_loss.png
new file mode 100644
index 000000000..6b3a7e96f
Binary files /dev/null and b/LossVal_loss.png differ
diff --git a/__MACOSX/._lfw b/__MACOSX/._lfw
new file mode 100644
index 000000000..d766cb749
Binary files /dev/null and b/__MACOSX/._lfw differ
diff --git a/bottleneck_features/DogResnet50Data.npz b/bottleneck_features/DogResnet50Data.npz
new file mode 100644
index 000000000..9d4b8c266
Binary files /dev/null and b/bottleneck_features/DogResnet50Data.npz differ
diff --git a/check_images.py b/check_images.py
new file mode 100644
index 000000000..720a220ab
--- /dev/null
+++ b/check_images.py
@@ -0,0 +1,21 @@
+from struct import unpack
+from tqdm import tqdm
+import os
+import glob
+
+fileList = glob.glob('./dogImages/*/*/*.*')
+
+import tensorflow.compat.v1 as tf
+tf.disable_v2_behavior()
+
+for i, image_name in enumerate(fileList):
+    print(i, image_name)
+
+    with tf.Graph().as_default():
+        image_contents = tf.read_file(image_name)
+        image = tf.image.decode_jpeg(image_contents, channels=3)
+        #
+        with tf.Session() as sess:
+            #sess.run(init_op)
+            sess.run(tf.global_variables_initializer())
+            tmp = sess.run(image)
diff --git a/dog_app.ipynb b/dog_app.ipynb
index 59ba0050b..b536d57ea 100644
--- a/dog_app.ipynb
+++ b/dog_app.ipynb
@@ -4,51 +4,6 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Artificial Intelligence Nanodegree\n",
-    "\n",
-    "## Convolutional Neural Networks\n",
-    "\n",
-    "## Project: Write an Algorithm for a Dog Identification App \n",
-    "\n",
-    "---\n",
-    "\n",
-    "In this notebook, some template code has already been provided for you, and you will need to implement additional functionality to successfully complete this project. You will not need to modify the included code beyond what is requested. Sections that begin with **'(IMPLEMENTATION)'** in the header indicate that the following block of code will require additional functionality which you must provide. Instructions will be provided for each section, and the specifics of the implementation are marked in the code block with a 'TODO' statement. Please be sure to read the instructions carefully! \n",
-    "\n",
-    "> **Note**: Once you have completed all of the code implementations, you need to finalize your work by exporting the iPython Notebook as an HTML document. Before exporting the notebook to html, all of the code cells need to have been run so that reviewers can see the final implementation and output. You can then export the notebook by using the menu above and navigating to  \\n\",\n",
-    "    \"**File -> Download as -> HTML (.html)**. Include the finished document along with this notebook as your submission.\n",
-    "\n",
-    "In addition to implementing code, there will be questions that you must answer which relate to the project and your implementation. Each section where you will answer a question is preceded by a **'Question X'** header. Carefully read each question and provide thorough answers in the following text boxes that begin with **'Answer:'**. Your project submission will be evaluated based on your answers to each of the questions and the implementation you provide.\n",
-    "\n",
-    ">**Note:** Code and Markdown cells can be executed using the **Shift + Enter** keyboard shortcut.  Markdown cells can be edited by double-clicking the cell to enter edit mode.\n",
-    "\n",
-    "The rubric contains _optional_ \"Stand Out Suggestions\" for enhancing the project beyond the minimum requirements. If you decide to pursue the \"Stand Out Suggestions\", you should include the code in this IPython notebook.\n",
-    "\n",
-    "\n",
-    "\n",
-    "---\n",
-    "### Why We're Here \n",
-    "\n",
-    "In this notebook, you will make the first steps towards developing an algorithm that could be used as part of a mobile or web app.  At the end of this project, your code will accept any user-supplied image as input.  If a dog is detected in the image, it will provide an estimate of the dog's breed.  If a human is detected, it will provide an estimate of the dog breed that is most resembling.  The image below displays potential sample output of your finished project (... but we expect that each student's algorithm will behave differently!). \n",
-    "\n",
-    "![Sample Dog Output](images/sample_dog_output.png)\n",
-    "\n",
-    "In this real-world setting, you will need to piece together a series of models to perform different tasks; for instance, the algorithm that detects humans in an image will be different from the CNN that infers dog breed.  There are many points of possible failure, and no perfect algorithm exists.  Your imperfect solution will nonetheless create a fun user experience!\n",
-    "\n",
-    "### The Road Ahead\n",
-    "\n",
-    "We break the notebook into separate steps.  Feel free to use the links below to navigate the notebook.\n",
-    "\n",
-    "* [Step 0](#step0): Import Datasets\n",
-    "* [Step 1](#step1): Detect Humans\n",
-    "* [Step 2](#step2): Detect Dogs\n",
-    "* [Step 3](#step3): Create a CNN to Classify Dog Breeds (from Scratch)\n",
-    "* [Step 4](#step4): Use a CNN to Classify Dog Breeds (using Transfer Learning)\n",
-    "* [Step 5](#step5): Create a CNN to Classify Dog Breeds (using Transfer Learning)\n",
-    "* [Step 6](#step6): Write your Algorithm\n",
-    "* [Step 7](#step7): Test Your Algorithm\n",
-    "\n",
-    "---\n",
-    "<a id='step0'></a>\n",
     "## Step 0: Import Datasets\n",
     "\n",
     "### Import Dog Dataset\n",
@@ -61,11 +16,34 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
+   "execution_count": 1,
+   "metadata": {},
    "outputs": [],
+   "source": [
+    "# !pip install sklearn\n",
+    "# !pip install opencv-python\n",
+    "# !pip install matplotlib\n",
+    "# !pip install tqdm\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "There are 133 total dog categories.\n",
+      "There are 8351 total dog images.\n",
+      "\n",
+      "There are 6680 training dog images.\n",
+      "There are 835 validation dog images.\n",
+      "There are 836 test dog images.\n"
+     ]
+    }
+   ],
    "source": [
     "from sklearn.datasets import load_files       \n",
     "from keras.utils import np_utils\n",
@@ -80,12 +58,12 @@
     "    return dog_files, dog_targets\n",
     "\n",
     "# load train, test, and validation datasets\n",
-    "train_files, train_targets = load_dataset('dogImages/train')\n",
-    "valid_files, valid_targets = load_dataset('dogImages/valid')\n",
-    "test_files, test_targets = load_dataset('dogImages/test')\n",
+    "train_files, train_targets = load_dataset(r'./dogImages/train')\n",
+    "valid_files, valid_targets = load_dataset(r'./dogImages/valid')\n",
+    "test_files, test_targets = load_dataset(r'./dogImages/test')\n",
     "\n",
     "# load list of dog names\n",
-    "dog_names = [item[20:-1] for item in sorted(glob(\"dogImages/train/*/\"))]\n",
+    "dog_names = [item[20:-1] for item in sorted(glob(\"./dogImages/train/*/\"))]\n",
     "\n",
     "# print statistics about the dataset\n",
     "print('There are %d total dog categories.' % len(dog_names))\n",
@@ -106,17 +84,23 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
-   "outputs": [],
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "There are 13233 total human images.\n"
+     ]
+    }
+   ],
    "source": [
     "import random\n",
     "random.seed(8675309)\n",
     "\n",
     "# load filenames in shuffled human dataset\n",
-    "human_files = np.array(glob(\"lfw/*/*\"))\n",
+    "human_files = np.array(glob(r\"./lfw/*/*\"))\n",
     "random.shuffle(human_files)\n",
     "\n",
     "# print statistics about the dataset\n",
@@ -127,7 +111,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "---\n",
+    "# ---\n",
     "<a id='step1'></a>\n",
     "## Step 1: Detect Humans\n",
     "\n",
@@ -138,18 +122,34 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
-   "outputs": [],
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Number of faces detected: 1\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": "<Figure size 432x288 with 1 Axes>",
+      "image/png": "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\n"
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
    "source": [
     "import cv2                \n",
     "import matplotlib.pyplot as plt                        \n",
     "%matplotlib inline                               \n",
     "\n",
     "# extract pre-trained face detector\n",
-    "face_cascade = cv2.CascadeClassifier('haarcascades/haarcascade_frontalface_alt.xml')\n",
+    "face_cascade = cv2.CascadeClassifier('./haarcascades/haarcascade_frontalface_alt.xml')\n",
     "\n",
     "# load color (BGR) image\n",
     "img = cv2.imread(human_files[3])\n",
@@ -190,10 +190,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
+   "execution_count": 5,
+   "metadata": {},
    "outputs": [],
    "source": [
     "# returns \"True\" if face is detected in image stored at img_path\n",
@@ -221,42 +219,28 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
-   "outputs": [],
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Accuracy on Dogs Files: 88% Accuracy on Human Files: 100%\n"
+     ]
+    }
+   ],
    "source": [
     "human_files_short = human_files[:100]\n",
     "dog_files_short = train_files[:100]\n",
     "# Do NOT modify the code above this line.\n",
     "\n",
     "## TODO: Test the performance of the face_detector algorithm \n",
-    "## on the images in human_files_short and dog_files_short."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "__Question 2:__ This algorithmic choice necessitates that we communicate to the user that we accept human images only when they provide a clear view of a face (otherwise, we risk having unneccessarily frustrated users!). In your opinion, is this a reasonable expectation to pose on the user? If not, can you think of a way to detect humans in images that does not necessitate an image with a clearly presented face?\n",
+    "## on the images in human_files_short and dog_files_short.\n",
+    "accuracy_dog = 100-np.array(list(map(face_detector, dog_files_short))).sum()\n",
+    "accuracy_human = np.array(list(map(face_detector, human_files_short))).sum()\n",
     "\n",
-    "__Answer:__\n",
-    "\n",
-    "We suggest the face detector from OpenCV as a potential way to detect human images in your algorithm, but you are free to explore other approaches, especially approaches that make use of deep learning :).  Please use the code cell below to design and test your own face detection algorithm.  If you decide to pursue this _optional_ task, report performance on each of the datasets."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
-   "outputs": [],
-   "source": [
-    "## (Optional) TODO: Report the performance of another  \n",
-    "## face detection algorithm on the LFW dataset\n",
-    "### Feel free to use as many code cells as needed."
+    "print('Accuracy on Dogs Files: {}% Accuracy on Human Files: {}%'.format(accuracy_dog, accuracy_human))"
    ]
   },
   {
@@ -272,16 +256,25 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
-   "outputs": [],
-   "source": [
-    "from keras.applications.resnet50 import ResNet50\n",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "2022-01-07 12:16:15.670953: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2 FMA\n",
+      "To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.\n"
+     ]
+    }
+   ],
+   "source": [
+    "from tensorflow.keras.applications.resnet50 import ResNet50\n",
+    "import ssl\n",
+    "ssl._create_default_https_context = ssl._create_unverified_context\n",
     "\n",
     "# define ResNet50 model\n",
-    "ResNet50_model = ResNet50(weights='imagenet')"
+    "ResNet50_mod = ResNet50(weights='imagenet')"
    ]
   },
   {
@@ -315,10 +308,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
+   "execution_count": 8,
+   "metadata": {},
    "outputs": [],
    "source": [
     "from keras.preprocessing import image                  \n",
@@ -334,7 +325,7 @@
     "\n",
     "def paths_to_tensor(img_paths):\n",
     "    list_of_tensors = [path_to_tensor(img_path) for img_path in tqdm(img_paths)]\n",
-    "    return np.vstack(list_of_tensors)"
+    "    return np.vstack(list_of_tensors)\n"
    ]
   },
   {
@@ -352,18 +343,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
+   "execution_count": 9,
+   "metadata": {},
    "outputs": [],
    "source": [
-    "from keras.applications.resnet50 import preprocess_input, decode_predictions\n",
+    "from tensorflow.keras.applications.resnet50 import preprocess_input, decode_predictions\n",
     "\n",
     "def ResNet50_predict_labels(img_path):\n",
     "    # returns prediction vector for image located at img_path\n",
     "    img = preprocess_input(path_to_tensor(img_path))\n",
-    "    return np.argmax(ResNet50_model.predict(img))"
+    "    return np.argmax(ResNet50_mod.predict(img))\n"
    ]
   },
   {
@@ -379,16 +368,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
+   "execution_count": 10,
+   "metadata": {},
    "outputs": [],
    "source": [
     "### returns \"True\" if a dog is detected in the image stored at img_path\n",
     "def dog_detector(img_path):\n",
     "    prediction = ResNet50_predict_labels(img_path)\n",
-    "    return ((prediction <= 268) & (prediction >= 151)) "
+    "    return ((prediction <= 268) & (prediction >= 151)) \n"
    ]
   },
   {
@@ -406,14 +393,26 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
-   "outputs": [],
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Accuracy on Dog Files: 100%\n",
+      "Accuracy on Human Files: 100%\n",
+      "Accuracy on Dog Files: 100%\n",
+      "Accuracy on Human Files: 100%\n"
+     ]
+    }
+   ],
    "source": [
     "### TODO: Test the performance of the dog_detector function\n",
-    "### on the images in human_files_short and dog_files_short."
+    "### on the images in human_files_short and dog_files_short.\n",
+    "accuracy_dog = (np.array(list(map(dog_detector, dog_files_short)))).mean()\n",
+    "accuracy_human = (1-(np.array(list(map(dog_detector,human_files_short))))).mean()\n",
+    "print('Accuracy on Dog Files: {:.0f}%\\nAccuracy on Human Files: {:.0f}%'.format(accuracy_dog*100,accuracy_human*100))\n"
    ]
   },
   {
@@ -458,11 +457,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
-   "outputs": [],
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "100%|██████████| 6680/6680 [01:08<00:00, 98.21it/s] \n",
+      "100%|██████████| 835/835 [00:08<00:00, 98.86it/s] \n",
+      "100%|██████████| 836/836 [00:08<00:00, 96.93it/s] \n"
+     ]
+    }
+   ],
    "source": [
     "from PIL import ImageFile                            \n",
     "ImageFile.LOAD_TRUNCATED_IMAGES = True                 \n",
@@ -473,140 +480,6 @@
     "test_tensors = paths_to_tensor(test_files).astype('float32')/255"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### (IMPLEMENTATION) Model Architecture\n",
-    "\n",
-    "Create a CNN to classify dog breed.  At the end of your code cell block, summarize the layers of your model by executing the line:\n",
-    "    \n",
-    "        model.summary()\n",
-    "\n",
-    "We have imported some Python modules to get you started, but feel free to import as many modules as you need.  If you end up getting stuck, here's a hint that specifies a model that trains relatively fast on CPU and attains >1% test accuracy in 5 epochs:\n",
-    "\n",
-    "![Sample CNN](images/sample_cnn.png)\n",
-    "           \n",
-    "__Question 4:__ Outline the steps you took to get to your final CNN architecture and your reasoning at each step.  If you chose to use the hinted architecture above, describe why you think that CNN architecture should work well for the image classification task.\n",
-    "\n",
-    "__Answer:__ "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
-   "outputs": [],
-   "source": [
-    "from keras.layers import Conv2D, MaxPooling2D, GlobalAveragePooling2D\n",
-    "from keras.layers import Dropout, Flatten, Dense\n",
-    "from keras.models import Sequential\n",
-    "\n",
-    "model = Sequential()\n",
-    "\n",
-    "### TODO: Define your architecture.\n",
-    "\n",
-    "model.summary()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Compile the Model"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
-   "outputs": [],
-   "source": [
-    "model.compile(optimizer='rmsprop', loss='categorical_crossentropy', metrics=['accuracy'])"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### (IMPLEMENTATION) Train the Model\n",
-    "\n",
-    "Train your model in the code cell below.  Use model checkpointing to save the model that attains the best validation loss.\n",
-    "\n",
-    "You are welcome to [augment the training data](https://blog.keras.io/building-powerful-image-classification-models-using-very-little-data.html), but this is not a requirement. "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
-   "outputs": [],
-   "source": [
-    "from keras.callbacks import ModelCheckpoint  \n",
-    "\n",
-    "### TODO: specify the number of epochs that you would like to use to train the model.\n",
-    "\n",
-    "epochs = ...\n",
-    "\n",
-    "### Do NOT modify the code below this line.\n",
-    "\n",
-    "checkpointer = ModelCheckpoint(filepath='saved_models/weights.best.from_scratch.hdf5', \n",
-    "                               verbose=1, save_best_only=True)\n",
-    "\n",
-    "model.fit(train_tensors, train_targets, \n",
-    "          validation_data=(valid_tensors, valid_targets),\n",
-    "          epochs=epochs, batch_size=20, callbacks=[checkpointer], verbose=1)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Load the Model with the Best Validation Loss"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
-   "outputs": [],
-   "source": [
-    "model.load_weights('saved_models/weights.best.from_scratch.hdf5')"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Test the Model\n",
-    "\n",
-    "Try out your model on the test dataset of dog images.  Ensure that your test accuracy is greater than 1%."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
-   "outputs": [],
-   "source": [
-    "# get index of predicted dog breed for each image in test set\n",
-    "dog_breed_predictions = [np.argmax(model.predict(np.expand_dims(tensor, axis=0))) for tensor in test_tensors]\n",
-    "\n",
-    "# report test accuracy\n",
-    "test_accuracy = 100*np.sum(np.array(dog_breed_predictions)==np.argmax(test_targets, axis=1))/len(dog_breed_predictions)\n",
-    "print('Test accuracy: %.4f%%' % test_accuracy)"
-   ]
-  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -623,12 +496,23 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
-   "outputs": [],
-   "source": [
-    "bottleneck_features = np.load('bottleneck_features/DogVGG16Data.npz')\n",
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "FileNotFoundError",
+     "evalue": "[Errno 2] No such file or directory: './bottleneck_features/DogVGG16Data.npz'",
+     "output_type": "error",
+     "traceback": [
+      "\u001B[0;31m---------------------------------------------------------------------------\u001B[0m",
+      "\u001B[0;31mFileNotFoundError\u001B[0m                         Traceback (most recent call last)",
+      "\u001B[0;32m/var/folders/dl/ybfk6f9d2vg12lwt1l6k23s80000gn/T/ipykernel_34245/1202609255.py\u001B[0m in \u001B[0;36m<module>\u001B[0;34m\u001B[0m\n\u001B[0;32m----> 1\u001B[0;31m \u001B[0mbottleneck_features\u001B[0m \u001B[0;34m=\u001B[0m \u001B[0mnp\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0mload\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0;34mr'./bottleneck_features/DogVGG16Data.npz'\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0m\u001B[1;32m      2\u001B[0m \u001B[0mtrain_VGG16\u001B[0m \u001B[0;34m=\u001B[0m \u001B[0mbottleneck_features\u001B[0m\u001B[0;34m[\u001B[0m\u001B[0;34m'train'\u001B[0m\u001B[0;34m]\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m      3\u001B[0m \u001B[0mvalid_VGG16\u001B[0m \u001B[0;34m=\u001B[0m \u001B[0mbottleneck_features\u001B[0m\u001B[0;34m[\u001B[0m\u001B[0;34m'valid'\u001B[0m\u001B[0;34m]\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m      4\u001B[0m \u001B[0mtest_VGG16\u001B[0m \u001B[0;34m=\u001B[0m \u001B[0mbottleneck_features\u001B[0m\u001B[0;34m[\u001B[0m\u001B[0;34m'test'\u001B[0m\u001B[0;34m]\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n",
+      "\u001B[0;32m~/Desktop/koktai/dog-project/venv/lib/python3.7/site-packages/numpy/lib/npyio.py\u001B[0m in \u001B[0;36mload\u001B[0;34m(file, mmap_mode, allow_pickle, fix_imports, encoding)\u001B[0m\n\u001B[1;32m    415\u001B[0m             \u001B[0mown_fid\u001B[0m \u001B[0;34m=\u001B[0m \u001B[0;32mFalse\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    416\u001B[0m         \u001B[0;32melse\u001B[0m\u001B[0;34m:\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0;32m--> 417\u001B[0;31m             \u001B[0mfid\u001B[0m \u001B[0;34m=\u001B[0m \u001B[0mstack\u001B[0m\u001B[0;34m.\u001B[0m\u001B[0menter_context\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mopen\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mos_fspath\u001B[0m\u001B[0;34m(\u001B[0m\u001B[0mfile\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m,\u001B[0m \u001B[0;34m\"rb\"\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m)\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[0m\u001B[1;32m    418\u001B[0m             \u001B[0mown_fid\u001B[0m \u001B[0;34m=\u001B[0m \u001B[0;32mTrue\u001B[0m\u001B[0;34m\u001B[0m\u001B[0;34m\u001B[0m\u001B[0m\n\u001B[1;32m    419\u001B[0m \u001B[0;34m\u001B[0m\u001B[0m\n",
+      "\u001B[0;31mFileNotFoundError\u001B[0m: [Errno 2] No such file or directory: './bottleneck_features/DogVGG16Data.npz'"
+     ]
+    }
+   ],
+   "source": [
+    "bottleneck_features = np.load(r'./bottleneck_features/DogVGG16Data.npz')\n",
     "train_VGG16 = bottleneck_features['train']\n",
     "valid_VGG16 = bottleneck_features['valid']\n",
     "test_VGG16 = bottleneck_features['test']"
@@ -646,11 +530,13 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
+    "from keras.layers import Conv2D, MaxPooling2D, GlobalAveragePooling2D\n",
+    "from keras.layers import Dropout, Flatten, Dense\n",
+    "from keras.models import Sequential\n",
+    "\n",
     "VGG16_model = Sequential()\n",
     "VGG16_model.add(GlobalAveragePooling2D(input_shape=train_VGG16.shape[1:]))\n",
     "VGG16_model.add(Dense(133, activation='softmax'))\n",
@@ -668,252 +554,140 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "VGG16_model.compile(loss='categorical_crossentropy', optimizer='rmsprop', metrics=['accuracy'])"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Train the Model"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
-   "outputs": [],
-   "source": [
-    "checkpointer = ModelCheckpoint(filepath='saved_models/weights.best.VGG16.hdf5', \n",
-    "                               verbose=1, save_best_only=True)\n",
-    "\n",
-    "VGG16_model.fit(train_VGG16, train_targets, \n",
-    "          validation_data=(valid_VGG16, valid_targets),\n",
-    "          epochs=20, batch_size=20, callbacks=[checkpointer], verbose=1)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
    "metadata": {},
-   "source": [
-    "### Load the Model with the Best Validation Loss"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
    "outputs": [],
    "source": [
-    "VGG16_model.load_weights('saved_models/weights.best.VGG16.hdf5')"
+    "from tensorflow.keras import callbacks\n",
+    "earlystopping = callbacks.EarlyStopping(monitor =\"val_loss\", \n",
+    "                                        mode =\"min\", patience = 5, \n",
+    "                                        restore_best_weights = True)\n",
+    " \n",
+    "r = VGG16_model.fit(train_VGG16, train_targets,\n",
+    "                    epochs = 25, batch_size = 20, validation_data=(valid_VGG16, valid_targets), \n",
+    "                    callbacks =[earlystopping])"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "### Test the Model\n",
-    "\n",
-    "Now, we can use the CNN to test how well it identifies breed within our test dataset of dog images.  We print the test accuracy below."
+    "### Train the Model"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
-   "outputs": [],
-   "source": [
-    "# get index of predicted dog breed for each image in test set\n",
-    "VGG16_predictions = [np.argmax(VGG16_model.predict(np.expand_dims(feature, axis=0))) for feature in test_VGG16]\n",
-    "\n",
-    "# report test accuracy\n",
-    "test_accuracy = 100*np.sum(np.array(VGG16_predictions)==np.argmax(test_targets, axis=1))/len(VGG16_predictions)\n",
-    "print('Test accuracy: %.4f%%' % test_accuracy)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
    "metadata": {},
-   "source": [
-    "### Predict Dog Breed with the Model"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
    "outputs": [],
    "source": [
-    "from extract_bottleneck_features import *\n",
+    "#from keras.callbacks import ModelCheckpoint  \n",
+    "#checkpointer = ModelCheckpoint(filepath=r'C:\\Users\\User\\Documents\\GitHub\\dog-project\\saved_models\\weights.best.VGG16.hdf5', \n",
+    "#                               verbose=1, save_best_only=True)\n",
     "\n",
-    "def VGG16_predict_breed(img_path):\n",
-    "    # extract bottleneck features\n",
-    "    bottleneck_feature = extract_VGG16(path_to_tensor(img_path))\n",
-    "    # obtain predicted vector\n",
-    "    predicted_vector = VGG16_model.predict(bottleneck_feature)\n",
-    "    # return dog breed that is predicted by the model\n",
-    "    return dog_names[np.argmax(predicted_vector)]"
+    "#r = VGG16_model.fit(train_VGG16, train_targets, \n",
+    "#          validation_data=(valid_VGG16, valid_targets),\n",
+    "#          epochs=20, batch_size=20, callbacks=[checkpointer], verbose=1)"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "---\n",
-    "<a id='step5'></a>\n",
-    "## Step 5: Create a CNN to Classify Dog Breeds (using Transfer Learning)\n",
-    "\n",
-    "You will now use transfer learning to create a CNN that can identify dog breed from images.  Your CNN must attain at least 60% accuracy on the test set.\n",
-    "\n",
-    "In Step 4, we used transfer learning to create a CNN using VGG-16 bottleneck features.  In this section, you must use the bottleneck features from a different pre-trained model.  To make things easier for you, we have pre-computed the features for all of the networks that are currently available in Keras:\n",
-    "- [VGG-19](https://s3-us-west-1.amazonaws.com/udacity-aind/dog-project/DogVGG19Data.npz) bottleneck features\n",
-    "- [ResNet-50](https://s3-us-west-1.amazonaws.com/udacity-aind/dog-project/DogResnet50Data.npz) bottleneck features\n",
-    "- [Inception](https://s3-us-west-1.amazonaws.com/udacity-aind/dog-project/DogInceptionV3Data.npz) bottleneck features\n",
-    "- [Xception](https://s3-us-west-1.amazonaws.com/udacity-aind/dog-project/DogXceptionData.npz) bottleneck features\n",
-    "\n",
-    "The files are encoded as such:\n",
-    "\n",
-    "    Dog{network}Data.npz\n",
-    "    \n",
-    "where `{network}`, in the above filename, can be one of `VGG19`, `Resnet50`, `InceptionV3`, or `Xception`.  Pick one of the above architectures, download the corresponding bottleneck features, and store the downloaded file in the `bottleneck_features/` folder in the repository.\n",
-    "\n",
-    "### (IMPLEMENTATION) Obtain Bottleneck Features\n",
-    "\n",
-    "In the code block below, extract the bottleneck features corresponding to the train, test, and validation sets by running the following:\n",
-    "\n",
-    "    bottleneck_features = np.load('bottleneck_features/Dog{network}Data.npz')\n",
-    "    train_{network} = bottleneck_features['train']\n",
-    "    valid_{network} = bottleneck_features['valid']\n",
-    "    test_{network} = bottleneck_features['test']"
+    "### Load the Model with the Best Validation Loss"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
-   "outputs": [],
-   "source": [
-    "### TODO: Obtain bottleneck features from another pre-trained CNN."
-   ]
-  },
-  {
-   "cell_type": "markdown",
    "metadata": {},
+   "outputs": [],
    "source": [
-    "### (IMPLEMENTATION) Model Architecture\n",
+    "# plot the loss\n",
+    "plt.plot(r.history['loss'], label='train loss')\n",
+    "plt.plot(r.history['val_loss'], label='val loss')\n",
+    "plt.legend()\n",
+    "plt.show()\n",
+    "plt.savefig('LossVal_loss')\n",
     "\n",
-    "Create a CNN to classify dog breed.  At the end of your code cell block, summarize the layers of your model by executing the line:\n",
-    "    \n",
-    "        <your model's name>.summary()\n",
-    "   \n",
-    "__Question 5:__ Outline the steps you took to get to your final CNN architecture and your reasoning at each step.  Describe why you think the architecture is suitable for the current problem.\n",
-    "\n",
-    "__Answer:__ \n",
-    "\n"
+    "# plot the accuracy\n",
+    "plt.plot(r.history['accuracy'], label='train acc')\n",
+    "plt.plot(r.history['val_accuracy'], label='val acc')\n",
+    "plt.legend()\n",
+    "plt.show()\n",
+    "plt.savefig('AccVal_acc')"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
-   "outputs": [],
-   "source": [
-    "### TODO: Define your architecture."
-   ]
-  },
-  {
-   "cell_type": "markdown",
    "metadata": {},
-   "source": [
-    "### (IMPLEMENTATION) Compile the Model"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
    "outputs": [],
    "source": [
-    "### TODO: Compile the model."
+    "VGG16_model.load_weights(r'./saved_models/weights.best.VGG16.hdf5')"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "### (IMPLEMENTATION) Train the Model\n",
-    "\n",
-    "Train your model in the code cell below.  Use model checkpointing to save the model that attains the best validation loss.  \n",
+    "### Test the Model\n",
     "\n",
-    "You are welcome to [augment the training data](https://blog.keras.io/building-powerful-image-classification-models-using-very-little-data.html), but this is not a requirement. "
+    "Now, we can use the CNN to test how well it identifies breed within our test dataset of dog images.  We print the test accuracy below."
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
-   "outputs": [],
-   "source": [
-    "### TODO: Train the model."
-   ]
-  },
-  {
-   "cell_type": "markdown",
    "metadata": {},
-   "source": [
-    "### (IMPLEMENTATION) Load the Model with the Best Validation Loss"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
    "outputs": [],
    "source": [
-    "### TODO: Load the model weights with the best validation loss."
+    "# get index of predicted dog breed for each image in test set\n",
+    "VGG16_predictions = [np.argmax(VGG16_model.predict(np.expand_dims(feature, axis=0))) for feature in test_VGG16]\n",
+    "\n",
+    "# report test accuracy\n",
+    "test_accuracy = 100*np.sum(np.array(VGG16_predictions)==np.argmax(test_targets, axis=1))/len(VGG16_predictions)\n",
+    "print('Test accuracy: %.4f%%' % test_accuracy)# report test accuracy\n"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "### (IMPLEMENTATION) Test the Model\n",
-    "\n",
-    "Try out your model on the test dataset of dog images. Ensure that your test accuracy is greater than 60%."
+    "### Predict Dog Breed with the Model"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
+   "execution_count": 21,
+   "metadata": {},
    "outputs": [],
    "source": [
-    "### TODO: Calculate classification accuracy on the test dataset."
+    "#from extract_bottleneck_features import *\n",
+    "\n",
+    "def extract_VGG16(tensor):\n",
+    "\tfrom keras.applications.vgg16 import VGG16, preprocess_input\n",
+    "\treturn VGG16(weights='imagenet', include_top=False).predict(preprocess_input(tensor))\n",
+    "\n",
+    "#def extract_Resnet50(tensor):\n",
+    "#\tfrom keras.applications.resnet import ResNet50, preprocess_input\n",
+    "#\treturn ResNet50(weights='imagenet', include_top=False).predict(preprocess_input(tensor))\n",
+    "\n",
+    "def VGG16_predict_breed(img_path):\n",
+    "    # extract bottleneck features\n",
+    "    bottleneck_feature = extract_VGG16(path_to_tensor(img_path))\n",
+    "    # obtain predicted vector\n",
+    "    predicted_vector = VGG16_model.predict(bottleneck_feature)\n",
+    "    # return dog breed that is predicted by the model\n",
+    "    return dog_names[np.argmax(predicted_vector)].split('.')[-1]"
    ]
   },
   {
@@ -938,14 +712,48 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
-   "outputs": [],
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "This image looks like a Labrador_retriever.\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
    "source": [
     "### TODO: Write a function that takes a path to an image as input\n",
-    "### and returns the dog breed that is predicted by the model."
+    "### and returns the dog breed that is predicted by the model.\n",
+    "### A function that takes a path to an image as input\n",
+    "### and returns the dog breed that is predicted by the model.\n",
+    "\n",
+    "\n",
+    "img_path =r\"C:\\Users\\User\\Documents\\GitHub\\dog-project\\images\\image.jpg\"\n",
+    "#img_path = dog_files_short[2]\n",
+    "def classify_dog_breed(img_path):\n",
+    "    img = path_to_tensor(img_path)\n",
+    "    predictions = VGG16_model.predict(extract_VGG16(img))\n",
+    "    prediction = np.argmax(predictions)\n",
+    "    dog_names[prediction].split('.')[-1]\n",
+    "    print('This image looks like a {}.'.format(dog_names[prediction].split('.')[-1]))\n",
+    "    return dog_names[prediction].split('.')[-1]\n",
+    "img = cv2.imread(img_path)\n",
+    "plt.imshow(cv2.cvtColor(img,cv2.COLOR_BGR2RGB))\n",
+    "prediction = classify_dog_breed(img_path)"
    ]
   },
   {
@@ -973,14 +781,63 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
-   "outputs": [],
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Neither Human nor Dog detected\n",
+      "\n",
+      "\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'Neither human nor dog'"
+      ]
+     },
+     "execution_count": 23,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
    "source": [
     "### TODO: Write your algorithm.\n",
-    "### Feel free to use as many code cells as needed."
+    "### Feel free to use as many code cells as needed.\n",
+    "def return_breed(img_path):\n",
+    "    if face_detector(img_path):\n",
+    "        print('Human Detected')\n",
+    "        print('\\n')\n",
+    "        return 'Human'\n",
+    "    elif dog_detector(img_path):\n",
+    "        print('Dog Detected')\n",
+    "        breed = classify_dog_breed(img_path)\n",
+    "        print('\\n')\n",
+    "        return breed\n",
+    "    else:\n",
+    "        print('Neither Human nor Dog detected')\n",
+    "        print('\\n')\n",
+    "        return 'Neither human nor dog'\n",
+    "\n",
+    "img_path = r'C:\\Users\\User\\Documents\\GitHub\\dog-project\\images\\st.jpg'    \n",
+    "img = cv2.imread(img_path)\n",
+    "plt.imshow(cv2.cvtColor(img,cv2.COLOR_BGR2RGB))\n",
+    "return_breed(img_path)"
    ]
   },
   {
@@ -1004,24 +861,160 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
-   "outputs": [],
+   "execution_count": 24,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "C:\\Users\\User\\Documents\\GitHub\\dog-project\\images\\dbdb.jpg\n",
+      "Dog Detected\n",
+      "This image looks like a German_pinscher.\n",
+      "\n",
+      "\n"
+     ]
+    }
+   ],
    "source": [
     "## TODO: Execute your algorithm from Step 6 on\n",
     "## at least 6 images on your computer.\n",
-    "## Feel free to use as many code cells as needed."
+    "## Feel free to use as many code cells as needed.\n",
+    "\n",
+    "for img_path in sorted(glob(r\"C:\\Users\\User\\Documents\\GitHub\\dog-project\\images\\dbdb.jpg\")):\n",
+    "    print(img_path)\n",
+    "    return_breed(img_path)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import tensorflow as tf\n",
+    "import os "
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# convert keras model to tflite \n",
+    "def get_file_size(file_path):\n",
+    "    size = os.path.getsize(file_path)\n",
+    "    return size\n",
+    "\n",
+    "def convert_bytes(size, unit=None):\n",
+    "    if unit == \"KB\":\n",
+    "        return print('File size: ' + str(round(size / 1024, 3)) + ' Kilobytes')\n",
+    "    elif unit == \"MB\":\n",
+    "        return print('File size: ' + str(round(size / (1024 * 1024), 3)) + ' Megabytes')\n",
+    "    else:\n",
+    "        return print('File size: ' + str(size) + ' bytes')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {
+    "scrolled": false
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "INFO:tensorflow:Assets written to: C:\\Users\\User\\AppData\\Local\\Temp\\tmpno5uuuum\\assets\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "WARNING:absl:Buffer deduplication procedure will be skipped when flatbuffer library is not properly loaded\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "File size: 267.98 Kilobytes\n",
+      "INFO:tensorflow:Assets written to: C:\\Users\\User\\AppData\\Local\\Temp\\tmplaivaxay\\assets\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "INFO:tensorflow:Assets written to: C:\\Users\\User\\AppData\\Local\\Temp\\tmplaivaxay\\assets\n",
+      "WARNING:absl:Buffer deduplication procedure will be skipped when flatbuffer library is not properly loaded\n"
+     ]
+    }
+   ],
+   "source": [
+    "from keras.models import load_model\n",
+    "model = load_model(r\"C:\\Users\\User\\Documents\\GitHub\\dog-project\\saved_models\\weights.best.VGG16.hdf5\")\n",
+    "\n",
+    "TF_LITE_MODEL_FILE_NAME = \"tflite_model.tflite\"\n",
+    "tf_lite_converter = tf.lite.TFLiteConverter.from_keras_model(model)\n",
+    "tflite_model = tf_lite_converter.convert()\n",
+    "tflite_model_name = TF_LITE_MODEL_FILE_NAME\n",
+    "open(tflite_model_name, \"wb\").write(tflite_model)\n",
+    "convert_bytes(get_file_size(TF_LITE_MODEL_FILE_NAME), \"KB\")\n",
+    "\n",
+    "# Convert the model.\n",
+    "converter = tf.lite.TFLiteConverter.from_keras_model(model)\n",
+    "tflite_model = converter.convert()\n",
+    "# or using another method\n",
+    "\n",
+    "# Save the model.\n",
+    "with open('tflite_model_another.tflite', 'wb') as f:\n",
+    "  f.write(tflite_model)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Input Shape: [  1   7   7 512]\n",
+      "Input Type: <class 'numpy.float32'>\n",
+      "Output Shape: [  1 133]\n",
+      "Output Type: <class 'numpy.float32'>\n"
+     ]
+    }
+   ],
+   "source": [
+    "interpreter = tf.lite.Interpreter(model_path = TF_LITE_MODEL_FILE_NAME)\n",
+    "input_details = interpreter.get_input_details()\n",
+    "output_details = interpreter.get_output_details()\n",
+    "print(\"Input Shape:\", input_details[0]['shape'])\n",
+    "print(\"Input Type:\", input_details[0]['dtype'])\n",
+    "print(\"Output Shape:\", output_details[0]['shape'])\n",
+    "print(\"Output Type:\", output_details[0]['dtype'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
   "anaconda-cloud": {},
   "kernelspec": {
-   "display_name": "dog-project",
+   "display_name": "Python 3",
    "language": "python",
-   "name": "dog-project"
+   "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {
@@ -1033,9 +1026,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.2"
+   "version": "3.8.12"
   }
  },
  "nbformat": 4,
  "nbformat_minor": 1
-}
+}
\ No newline at end of file
diff --git a/extract_bottleneck_features.py b/extract_bottleneck_features.py
index 000f7db1e..b774426b8 100644
--- a/extract_bottleneck_features.py
+++ b/extract_bottleneck_features.py
@@ -7,7 +7,7 @@ def extract_VGG19(tensor):
 	return VGG19(weights='imagenet', include_top=False).predict(preprocess_input(tensor))
 
 def extract_Resnet50(tensor):
-	from keras.applications.resnet50 import ResNet50, preprocess_input
+	from keras.applications.resnet import ResNet50, preprocess_input
 	return ResNet50(weights='imagenet', include_top=False).predict(preprocess_input(tensor))
 
 def extract_Xception(tensor):
diff --git a/images/asd.jpg b/images/asd.jpg
new file mode 100644
index 000000000..4bf040ed8
Binary files /dev/null and b/images/asd.jpg differ
diff --git a/images/bb.jpg b/images/bb.jpg
new file mode 100644
index 000000000..57907cd7d
Binary files /dev/null and b/images/bb.jpg differ
diff --git a/images/cat.jpg b/images/cat.jpg
new file mode 100644
index 000000000..4e2d8bfae
Binary files /dev/null and b/images/cat.jpg differ
diff --git a/images/db.jpg b/images/db.jpg
new file mode 100644
index 000000000..212a89027
Binary files /dev/null and b/images/db.jpg differ
diff --git a/images/dbd.jpg b/images/dbd.jpg
new file mode 100644
index 000000000..6d516a693
Binary files /dev/null and b/images/dbd.jpg differ
diff --git a/images/dbdb.jpg b/images/dbdb.jpg
new file mode 100644
index 000000000..fa5e2ddfe
Binary files /dev/null and b/images/dbdb.jpg differ
diff --git a/images/dp.jpg b/images/dp.jpg
new file mode 100644
index 000000000..73e5bb18f
Binary files /dev/null and b/images/dp.jpg differ
diff --git a/images/hhh.jpg b/images/hhh.jpg
new file mode 100644
index 000000000..4aca8fc6d
Binary files /dev/null and b/images/hhh.jpg differ
diff --git a/images/image.jpg b/images/image.jpg
new file mode 100644
index 000000000..f036ae02a
Binary files /dev/null and b/images/image.jpg differ
diff --git a/images/qqq.jpg b/images/qqq.jpg
new file mode 100644
index 000000000..f890c0af9
Binary files /dev/null and b/images/qqq.jpg differ
diff --git a/images/rr.jpg b/images/rr.jpg
new file mode 100644
index 000000000..33d8367d9
Binary files /dev/null and b/images/rr.jpg differ
diff --git a/images/rt.jpg b/images/rt.jpg
new file mode 100644
index 000000000..98e77ffd0
Binary files /dev/null and b/images/rt.jpg differ
diff --git a/images/st.jpg b/images/st.jpg
new file mode 100644
index 000000000..02790cf3f
Binary files /dev/null and b/images/st.jpg differ
diff --git a/images/tt.jpg b/images/tt.jpg
new file mode 100644
index 000000000..c49e4e6db
Binary files /dev/null and b/images/tt.jpg differ
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 000000000..46f82599a
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,101 @@
+absl-py==0.15.0
+argon2-cffi==21.3.0
+argon2-cffi-bindings==21.2.0
+astunparse==1.6.3
+attrs==21.4.0
+backcall==0.2.0
+bleach==4.1.0
+cachetools==4.2.4
+certifi==2020.6.20
+cffi==1.15.0
+charset-normalizer==2.0.10
+colorama==0.4.4
+cycler==0.11.0
+debugpy==1.5.1
+decorator==5.1.0
+defusedxml==0.7.1
+entrypoints==0.3
+flatbuffers==1.12
+fonttools==4.28.5
+gast==0.3.3
+google-auth==2.3.3
+google-auth-oauthlib==0.4.6
+google-pasta==0.2.0
+grpcio==1.32.0
+h5py==2.10.0
+idna==3.3
+importlib-metadata==4.10.0
+importlib-resources==5.4.0
+ipykernel==6.6.1
+ipython==7.31.0
+ipython-genutils==0.2.0
+jedi==0.18.1
+Jinja2==3.0.3
+joblib==1.1.0
+jsonschema==4.3.3
+jupyter-client==7.1.0
+jupyter-core==4.9.1
+jupyterlab-pygments==0.1.2
+Keras-Preprocessing==1.1.2
+kiwisolver==1.3.2
+Markdown==3.3.6
+MarkupSafe==2.0.1
+matplotlib==3.5.1
+matplotlib-inline==0.1.3
+mistune==0.8.4
+nbclient==0.5.9
+nbconvert==6.4.0
+nbformat==5.1.3
+nest-asyncio==1.5.4
+notebook==6.4.6
+numpy==1.19.5
+oauthlib==3.1.1
+opt-einsum==3.3.0
+packaging==21.3
+pandas==1.3.5
+pandocfilters==1.5.0
+parso==0.8.3
+pickleshare==0.7.5
+Pillow==9.0.0
+prometheus-client==0.12.0
+prompt-toolkit==3.0.24
+protobuf==3.19.1
+pyasn1==0.4.8
+pyasn1-modules==0.2.8
+pycparser==2.21
+Pygments==2.11.2
+pyparsing==3.0.6
+pyrsistent==0.18.0
+python-dateutil==2.8.2
+pytz==2021.3
+pywin32==303
+pywinpty==1.1.6
+pyzmq==22.3.0
+requests==2.27.1
+requests-oauthlib==1.3.0
+rsa==4.8
+scikit-learn==1.0.2
+scipy==1.7.3
+Send2Trash==1.8.0
+six==1.15.0
+sklearn==0.0
+tensorboard==2.7.0
+tensorboard-data-server==0.6.1
+tensorboard-plugin-wit==1.8.1
+tensorflow-estimator==2.4.0
+tensorflow-gpu==2.4.0
+termcolor==1.1.0
+terminado==0.12.1
+testpath==0.5.0
+threadpoolctl==3.0.0
+tornado==6.1
+tqdm==4.62.3
+traitlets==5.1.1
+typing-extensions==3.7.4.3
+urllib3==1.26.7
+wcwidth==0.2.5
+webencodings==0.5.1
+Werkzeug==2.0.2
+wincertstore==0.2
+wrapt==1.12.1
+zipp==3.7.0
diff --git a/saved_models/convert.py b/saved_models/convert.py
new file mode 100644
index 000000000..2a3c7475f
--- /dev/null
+++ b/saved_models/convert.py
@@ -0,0 +1,15 @@
+from keras.models import load_model
+import tensorflow as tf
+
+model = load_model("catdog.h5")
+
+
+converter = tf.lite.TFLiteConverter.from_keras_model(model)
+tflite_model = converter.convert()
+
+print("model converted")
+
+# Save the model.
+with open('model.tflite', 'wb') as f:
+  f.write(tflite_model)
+  
diff --git a/saved_models/inf.py b/saved_models/inf.py
new file mode 100644
index 000000000..60d023e87
--- /dev/null
+++ b/saved_models/inf.py
@@ -0,0 +1,30 @@
+import numpy as np
+import tensorflow as tf
+import cv2
+
+img = cv2.imread("dog.jpeg")
+img = cv2.resize(img, (128,128))
+img = np.array(img, dtype="float32")
+img = np.reshape(img, (1,128,128,3))
+
+
+# Load the TFLite model and allocate tensors.
+interpreter = tf.lite.Interpreter(model_path="model.tflite")
+interpreter.allocate_tensors()
+
+# Get input and output tensors.
+input_details = interpreter.get_input_details()
+output_details = interpreter.get_output_details()
+
+# Test the model on random input data.
+input_shape = input_details[0]['shape']
+
+print("*"*50, input_details)
+interpreter.set_tensor(input_details[0]['index'], img)
+
+interpreter.invoke()
+
+# The function `get_tensor()` returns a copy of the tensor data.
+# Use `tensor()` in order to get a pointer to the tensor.
+output_data = interpreter.get_tensor(output_details[0]['index'])
+print(output_data)
diff --git a/saved_models/weights.best.ResNet50.hdf5 b/saved_models/weights.best.ResNet50.hdf5
new file mode 100644
index 000000000..597a04877
Binary files /dev/null and b/saved_models/weights.best.ResNet50.hdf5 differ
diff --git a/tflite_model.tflite b/tflite_model.tflite
new file mode 100644
index 000000000..2df45f961
Binary files /dev/null and b/tflite_model.tflite differ
diff --git a/tflite_model_another.tflite b/tflite_model_another.tflite
new file mode 100644
index 000000000..2df45f961
Binary files /dev/null and b/tflite_model_another.tflite differ
diff --git a/train.ipynb b/train.ipynb
new file mode 100644
index 000000000..23b576502
--- /dev/null
+++ b/train.ipynb
@@ -0,0 +1,575 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Requirement already satisfied: absl-py==0.15.0 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 1)) (0.15.0)\n",
+      "Requirement already satisfied: argon2-cffi==21.3.0 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 2)) (21.3.0)\n",
+      "Requirement already satisfied: argon2-cffi-bindings==21.2.0 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 3)) (21.2.0)\n",
+      "Requirement already satisfied: astunparse==1.6.3 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 4)) (1.6.3)\n",
+      "Requirement already satisfied: attrs==21.4.0 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 5)) (21.4.0)\n",
+      "Requirement already satisfied: backcall==0.2.0 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 6)) (0.2.0)\n",
+      "Requirement already satisfied: bleach==4.1.0 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 7)) (4.1.0)\n",
+      "Requirement already satisfied: cachetools==4.2.4 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 8)) (4.2.4)\n",
+      "Requirement already satisfied: certifi==2020.6.20 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 9)) (2020.6.20)\n",
+      "Requirement already satisfied: cffi==1.15.0 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 10)) (1.15.0)\n",
+      "Requirement already satisfied: charset-normalizer==2.0.10 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 11)) (2.0.10)\n",
+      "Requirement already satisfied: colorama==0.4.4 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 12)) (0.4.4)\n",
+      "Requirement already satisfied: cycler==0.11.0 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 13)) (0.11.0)\n",
+      "Requirement already satisfied: debugpy==1.5.1 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 14)) (1.5.1)\n",
+      "Requirement already satisfied: decorator==5.1.0 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 15)) (5.1.0)\n",
+      "Requirement already satisfied: defusedxml==0.7.1 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 16)) (0.7.1)\n",
+      "Requirement already satisfied: entrypoints==0.3 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 17)) (0.3)\n",
+      "Requirement already satisfied: flatbuffers==1.12 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 18)) (1.12)\n",
+      "Requirement already satisfied: fonttools==4.28.5 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 19)) (4.28.5)\n",
+      "Requirement already satisfied: gast==0.3.3 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 20)) (0.3.3)\n",
+      "Requirement already satisfied: google-auth==2.3.3 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 21)) (2.3.3)\n",
+      "Requirement already satisfied: google-auth-oauthlib==0.4.6 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 22)) (0.4.6)\n",
+      "Requirement already satisfied: google-pasta==0.2.0 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 23)) (0.2.0)\n",
+      "Requirement already satisfied: grpcio==1.32.0 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 24)) (1.32.0)\n",
+      "Requirement already satisfied: h5py==2.10.0 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 25)) (2.10.0)\n",
+      "Requirement already satisfied: idna==3.3 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 26)) (3.3)\n",
+      "Requirement already satisfied: importlib-metadata==4.10.0 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 27)) (4.10.0)\n",
+      "Requirement already satisfied: importlib-resources==5.4.0 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 28)) (5.4.0)\n",
+      "Requirement already satisfied: ipykernel==6.6.1 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 29)) (6.6.1)\n",
+      "Requirement already satisfied: ipython==7.31.0 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 30)) (7.31.0)\n",
+      "Requirement already satisfied: ipython-genutils==0.2.0 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 31)) (0.2.0)\n",
+      "Requirement already satisfied: jedi==0.18.1 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 32)) (0.18.1)\n",
+      "Requirement already satisfied: Jinja2==3.0.3 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 33)) (3.0.3)\n",
+      "Requirement already satisfied: joblib==1.1.0 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 34)) (1.1.0)\n",
+      "Requirement already satisfied: jsonschema==4.3.3 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 35)) (4.3.3)\n",
+      "Requirement already satisfied: jupyter-client==7.1.0 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 36)) (7.1.0)\n",
+      "Requirement already satisfied: jupyter-core==4.9.1 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 37)) (4.9.1)\n",
+      "Requirement already satisfied: jupyterlab-pygments==0.1.2 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 38)) (0.1.2)\n",
+      "Requirement already satisfied: Keras-Preprocessing==1.1.2 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 39)) (1.1.2)\n",
+      "Requirement already satisfied: kiwisolver==1.3.2 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 40)) (1.3.2)\n",
+      "Requirement already satisfied: Markdown==3.3.6 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 41)) (3.3.6)\n",
+      "Requirement already satisfied: MarkupSafe==2.0.1 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 42)) (2.0.1)\n",
+      "Requirement already satisfied: matplotlib==3.5.1 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 43)) (3.5.1)\n",
+      "Requirement already satisfied: matplotlib-inline==0.1.3 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 44)) (0.1.3)\n",
+      "Requirement already satisfied: mistune==0.8.4 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 45)) (0.8.4)\n",
+      "Requirement already satisfied: nbclient==0.5.9 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 46)) (0.5.9)\n",
+      "Requirement already satisfied: nbconvert==6.4.0 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 47)) (6.4.0)\n",
+      "Requirement already satisfied: nbformat==5.1.3 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 48)) (5.1.3)\n",
+      "Requirement already satisfied: nest-asyncio==1.5.4 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 49)) (1.5.4)\n",
+      "Requirement already satisfied: notebook==6.4.6 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 50)) (6.4.6)\n",
+      "Requirement already satisfied: numpy==1.19.5 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 51)) (1.19.5)\n",
+      "Requirement already satisfied: oauthlib==3.1.1 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 52)) (3.1.1)\n",
+      "Requirement already satisfied: opt-einsum==3.3.0 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 53)) (3.3.0)\n",
+      "Requirement already satisfied: packaging==21.3 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 54)) (21.3)\n",
+      "Requirement already satisfied: pandas==1.3.5 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 55)) (1.3.5)\n",
+      "Requirement already satisfied: pandocfilters==1.5.0 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 56)) (1.5.0)\n",
+      "Requirement already satisfied: parso==0.8.3 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 57)) (0.8.3)\n",
+      "Requirement already satisfied: pickleshare==0.7.5 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 58)) (0.7.5)\n",
+      "Requirement already satisfied: Pillow==9.0.0 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 59)) (9.0.0)\n",
+      "Requirement already satisfied: prometheus-client==0.12.0 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 60)) (0.12.0)\n",
+      "Requirement already satisfied: prompt-toolkit==3.0.24 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 61)) (3.0.24)\n",
+      "Requirement already satisfied: protobuf==3.19.1 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 62)) (3.19.1)"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "WARNING: Ignoring invalid distribution -illow (c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages)\n",
+      "WARNING: Ignoring invalid distribution -illow (c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages)\n",
+      "WARNING: Ignoring invalid distribution -illow (c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages)\n",
+      "WARNING: Ignoring invalid distribution -illow (c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages)\n",
+      "WARNING: Ignoring invalid distribution -illow (c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages)\n",
+      "WARNING: Ignoring invalid distribution -illow (c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "Requirement already satisfied: pyasn1==0.4.8 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 63)) (0.4.8)\n",
+      "Requirement already satisfied: pyasn1-modules==0.2.8 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 64)) (0.2.8)\n",
+      "Requirement already satisfied: pycparser==2.21 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 65)) (2.21)\n",
+      "Requirement already satisfied: Pygments==2.11.2 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 66)) (2.11.2)\n",
+      "Requirement already satisfied: pyparsing==3.0.6 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 67)) (3.0.6)\n",
+      "Requirement already satisfied: pyrsistent==0.18.0 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 68)) (0.18.0)\n",
+      "Requirement already satisfied: python-dateutil==2.8.2 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 69)) (2.8.2)\n",
+      "Requirement already satisfied: pytz==2021.3 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 70)) (2021.3)\n",
+      "Requirement already satisfied: pywin32==303 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 71)) (303)\n",
+      "Requirement already satisfied: pywinpty==1.1.6 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 72)) (1.1.6)\n",
+      "Requirement already satisfied: pyzmq==22.3.0 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 73)) (22.3.0)\n",
+      "Requirement already satisfied: requests==2.27.1 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 74)) (2.27.1)\n",
+      "Requirement already satisfied: requests-oauthlib==1.3.0 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 75)) (1.3.0)\n",
+      "Requirement already satisfied: rsa==4.8 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 76)) (4.8)\n",
+      "Requirement already satisfied: scikit-learn==1.0.2 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 77)) (1.0.2)\n",
+      "Requirement already satisfied: scipy==1.7.3 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 78)) (1.7.3)\n",
+      "Requirement already satisfied: Send2Trash==1.8.0 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 79)) (1.8.0)\n",
+      "Requirement already satisfied: six==1.15.0 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 80)) (1.15.0)\n",
+      "Requirement already satisfied: sklearn==0.0 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 81)) (0.0)\n",
+      "Requirement already satisfied: tensorboard==2.7.0 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 82)) (2.7.0)\n",
+      "Requirement already satisfied: tensorboard-data-server==0.6.1 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 83)) (0.6.1)\n",
+      "Requirement already satisfied: tensorboard-plugin-wit==1.8.1 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 84)) (1.8.1)\n",
+      "Requirement already satisfied: tensorflow-estimator==2.4.0 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 85)) (2.4.0)\n",
+      "Requirement already satisfied: tensorflow-gpu==2.4.0 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 86)) (2.4.0)\n",
+      "Requirement already satisfied: termcolor==1.1.0 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 87)) (1.1.0)\n",
+      "Requirement already satisfied: terminado==0.12.1 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 88)) (0.12.1)\n",
+      "Requirement already satisfied: testpath==0.5.0 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 89)) (0.5.0)\n",
+      "Requirement already satisfied: threadpoolctl==3.0.0 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 90)) (3.0.0)\n",
+      "Requirement already satisfied: tornado==6.1 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 91)) (6.1)\n",
+      "Requirement already satisfied: tqdm==4.62.3 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 92)) (4.62.3)\n",
+      "Requirement already satisfied: traitlets==5.1.1 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 93)) (5.1.1)\n",
+      "Requirement already satisfied: typing-extensions==3.7.4.3 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 94)) (3.7.4.3)\n",
+      "Requirement already satisfied: urllib3==1.26.7 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 95)) (1.26.7)\n",
+      "Requirement already satisfied: wcwidth==0.2.5 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 96)) (0.2.5)\n",
+      "Requirement already satisfied: webencodings==0.5.1 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 97)) (0.5.1)\n",
+      "Requirement already satisfied: Werkzeug==2.0.2 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 98)) (2.0.2)\n",
+      "Requirement already satisfied: wincertstore==0.2 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 99)) (0.2)\n",
+      "Requirement already satisfied: wrapt==1.12.1 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 100)) (1.12.1)\n",
+      "Requirement already satisfied: zipp==3.7.0 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from -r requirements.txt (line 101)) (3.7.0)\n",
+      "Requirement already satisfied: wheel<1.0,>=0.23.0 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from astunparse==1.6.3->-r requirements.txt (line 4)) (0.37.0)\n",
+      "Requirement already satisfied: setuptools>=40.3.0 in c:\\users\\user\\anaconda3\\envs\\tensorflow\\lib\\site-packages (from google-auth==2.3.3->-r requirements.txt (line 21)) (58.0.4)\n"
+     ]
+    }
+   ],
+   "source": [
+    "!pip install -r requirements.txt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "ImportError",
+     "evalue": "cannot import name 'LayerNormalization' from 'tensorflow.python.keras.layers.normalization' (C:\\Users\\User\\anaconda3\\envs\\tensorflow\\lib\\site-packages\\tensorflow\\python\\keras\\layers\\normalization\\__init__.py)",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mImportError\u001b[0m                               Traceback (most recent call last)",
+      "\u001b[1;32m~\\AppData\\Local\\Temp/ipykernel_25584/112537649.py\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m      1\u001b[0m \u001b[1;31m## Import libraries and enable GPU in tensorflow\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      2\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 3\u001b[1;33m \u001b[1;32mimport\u001b[0m \u001b[0mtensorflow\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0mtf\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m      4\u001b[0m \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      5\u001b[0m     \u001b[0mphysical_devices\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mtf\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mconfig\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mlist_physical_devices\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'GPU'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;32m~\\anaconda3\\envs\\tensorflow\\lib\\site-packages\\tensorflow\\__init__.py\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m     39\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0msys\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0m_sys\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     40\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 41\u001b[1;33m \u001b[1;32mfrom\u001b[0m \u001b[0mtensorflow\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpython\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mtools\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mmodule_util\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0m_module_util\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     42\u001b[0m \u001b[1;32mfrom\u001b[0m \u001b[0mtensorflow\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpython\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mutil\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mlazy_loader\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mLazyLoader\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0m_LazyLoader\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     43\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;32m~\\anaconda3\\envs\\tensorflow\\lib\\site-packages\\tensorflow\\python\\__init__.py\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m     46\u001b[0m \u001b[1;32mfrom\u001b[0m \u001b[0mtensorflow\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpython\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mdata\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     47\u001b[0m \u001b[1;32mfrom\u001b[0m \u001b[0mtensorflow\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpython\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mdistribute\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 48\u001b[1;33m \u001b[1;32mfrom\u001b[0m \u001b[0mtensorflow\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpython\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mkeras\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     49\u001b[0m \u001b[1;32mfrom\u001b[0m \u001b[0mtensorflow\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpython\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfeature_column\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mfeature_column_lib\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0mfeature_column\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     50\u001b[0m \u001b[1;32mfrom\u001b[0m \u001b[0mtensorflow\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpython\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mlayers\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mlayers\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;32m~\\anaconda3\\envs\\tensorflow\\lib\\site-packages\\tensorflow\\python\\keras\\__init__.py\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m     25\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     26\u001b[0m \u001b[1;31m# See b/110718070#comment18 for more details about this import.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 27\u001b[1;33m \u001b[1;32mfrom\u001b[0m \u001b[0mtensorflow\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpython\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mkeras\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mmodels\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     28\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     29\u001b[0m \u001b[1;32mfrom\u001b[0m \u001b[0mtensorflow\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpython\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mkeras\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mengine\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0minput_layer\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mInput\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;32m~\\anaconda3\\envs\\tensorflow\\lib\\site-packages\\tensorflow\\python\\keras\\models.py\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m     25\u001b[0m \u001b[1;32mfrom\u001b[0m \u001b[0mtensorflow\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpython\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mkeras\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0moptimizer_v1\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     26\u001b[0m \u001b[1;32mfrom\u001b[0m \u001b[0mtensorflow\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpython\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mkeras\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mengine\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mfunctional\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 27\u001b[1;33m \u001b[1;32mfrom\u001b[0m \u001b[0mtensorflow\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpython\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mkeras\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mengine\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0msequential\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     28\u001b[0m \u001b[1;32mfrom\u001b[0m \u001b[0mtensorflow\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpython\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mkeras\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mengine\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mtraining\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     29\u001b[0m \u001b[1;32mfrom\u001b[0m \u001b[0mtensorflow\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpython\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mkeras\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mengine\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mtraining_v1\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;32m~\\anaconda3\\envs\\tensorflow\\lib\\site-packages\\tensorflow\\python\\keras\\engine\\sequential.py\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m     26\u001b[0m \u001b[1;32mfrom\u001b[0m \u001b[0mtensorflow\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpython\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mframework\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mops\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     27\u001b[0m \u001b[1;32mfrom\u001b[0m \u001b[0mtensorflow\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpython\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mframework\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mtensor_util\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 28\u001b[1;33m \u001b[1;32mfrom\u001b[0m \u001b[0mtensorflow\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpython\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mkeras\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mlayers\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0mlayer_module\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     29\u001b[0m \u001b[1;32mfrom\u001b[0m \u001b[0mtensorflow\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpython\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mkeras\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mengine\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mbase_layer\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     30\u001b[0m \u001b[1;32mfrom\u001b[0m \u001b[0mtensorflow\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpython\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mkeras\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mengine\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mfunctional\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;32m~\\anaconda3\\envs\\tensorflow\\lib\\site-packages\\tensorflow\\python\\keras\\layers\\__init__.py\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m    175\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    176\u001b[0m \u001b[1;31m# Normalization layers.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 177\u001b[1;33m \u001b[1;32mfrom\u001b[0m \u001b[0mtensorflow\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpython\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mkeras\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mlayers\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mnormalization\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mLayerNormalization\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    178\u001b[0m \u001b[1;32mfrom\u001b[0m \u001b[0mtensorflow\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpython\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mkeras\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mlayers\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mnormalization_v2\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mSyncBatchNormalization\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    179\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;31mImportError\u001b[0m: cannot import name 'LayerNormalization' from 'tensorflow.python.keras.layers.normalization' (C:\\Users\\User\\anaconda3\\envs\\tensorflow\\lib\\site-packages\\tensorflow\\python\\keras\\layers\\normalization\\__init__.py)"
+     ]
+    }
+   ],
+   "source": [
+    "## Import libraries and enable GPU in tensorflow\n",
+    "\n",
+    "import tensorflow as tf\n",
+    "try:\n",
+    "    physical_devices = tf.config.list_physical_devices('GPU')\n",
+    "    tf.config.experimental.set_memory_growth(physical_devices[0], True)\n",
+    "except:\n",
+    "    pass\n",
+    "\n",
+    "print(\"Num GPUs Available: \", len(tf.config.list_physical_devices('GPU')))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "# Import libraries\n",
+    "\n",
+    "import pathlib\n",
+    "import matplotlib.pyplot as plt\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import tensorflow as tf\n",
+    "from tensorflow.keras import layers\n",
+    "\n",
+    "# Compile and Train\n",
+    "from tensorflow.keras.optimizers import RMSprop,SGD,Adam\n",
+    "from tensorflow.keras.callbacks import ModelCheckpoint, EarlyStopping, ReduceLROnPlateau\n",
+    "\n",
+    "from PIL import ImageFile\n",
+    "ImageFile.LOAD_TRUNCATED_IMAGES = True"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "# Define the dataset path\n",
+    "\n",
+    "data_dir = \"./dogImages/train\"\n",
+    "print(data_dir)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "# Degine some parameter\n",
+    "img_height = 224\n",
+    "img_width = 224\n",
+    "batch_size = 128 ## Images will pass into the network per epochs\n",
+    "\n",
+    "# Load images into the train dataloader\n",
+    "train_ds = tf.keras.preprocessing.image_dataset_from_directory(\n",
+    "  r\"C:\\Users\\User\\Documents\\GitHub\\dog-project\\dogImages\\dogImages\\train\",\n",
+    "  labels='inferred',\n",
+    "  label_mode='categorical',\n",
+    "  # validation_split=0.2, #use 80% as training dataset\n",
+    "  # subset=\"training\",\n",
+    "  seed=123,\n",
+    "  image_size=(img_height, img_width),\n",
+    "  batch_size=batch_size\n",
+    ")\n",
+    "\n",
+    "class_names = train_ds.class_names"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "# Degine some parameter\n",
+    "img_height = 224\n",
+    "img_width = 224\n",
+    "batch_size = 1 ## Images will pass into the network per epochs\n",
+    "\n",
+    "# Load images into the validation dataloader\n",
+    "val_ds = tf.keras.preprocessing.image_dataset_from_directory(\n",
+    "  r\"C:\\Users\\User\\Documents\\GitHub\\dog-project\\dogImages\\dogImages\\valid\",\n",
+    "  labels='inferred',\n",
+    "  label_mode='categorical',\n",
+    "  # validation_split=0.2, #use 20% as training dataset\n",
+    "  # subset=\"validation\",\n",
+    "  seed=123,\n",
+    "  image_size=(img_height, img_width),\n",
+    "  batch_size=batch_size\n",
+    ")\n",
+    "\n",
+    "class_names = val_ds.class_names"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "# Show images to make sure images loaded are correct\n",
+    "\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "plt.figure(figsize=(10, 10))\n",
+    "for images, labels in train_ds.take(1):\n",
+    "    for i in range(9):\n",
+    "        ax = plt.subplot(3, 3, i + 1)\n",
+    "        plt.imshow(images[i].numpy().astype(\"uint8\"))\n",
+    "#         plt.title(class_names[labels[i]])\n",
+    "        plt.axis(\"off\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "# Check the dataloader parameter\n",
+    "\n",
+    "for image_batch, labels_batch in train_ds:\n",
+    "    print(image_batch.shape)\n",
+    "    print(labels_batch.shape)\n",
+    "    break"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "# Normalize the images\n",
+    "## normal images => 0-255\n",
+    "## normalized images => 0-1\n",
+    "\n",
+    "## example:\n",
+    "## 127 in normal image === 0.5 in normalized image\n",
+    "\n",
+    "## we normalize images to reduce the computation cost.\n",
+    "\n",
+    "normalization_layer = tf.keras.layers.experimental.preprocessing.Rescaling(1./255)\n",
+    "normalized_ds = train_ds.map(lambda x, y: (normalization_layer(x), y))\n",
+    "image_batch, labels_batch = next(iter(normalized_ds))\n",
+    "first_image = image_batch[0]\n",
+    "print(np.min(first_image), np.max(first_image))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "AUTOTUNE = tf.data.AUTOTUNE\n",
+    "train_ds = train_ds.cache().prefetch(buffer_size=AUTOTUNE)\n",
+    "val_ds = val_ds.cache().prefetch(buffer_size=AUTOTUNE)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "# create the base model\n",
+    "import ssl\n",
+    "ssl._create_default_https_context = ssl._create_unverified_context\n",
+    "\n",
+    "base_model = tf.keras.applications.VGG16(weights='imagenet', include_top=False)\n",
+    "base_model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "# freeze layers -> we train again from scratch\n",
+    "for layer in base_model.layers[:143]:\n",
+    "    layer.trainable = False\n",
+    "\n",
+    "# let's visualize layer names and layer indices to see how many layers\n",
+    "# we should freeze:\n",
+    "for i, layer in enumerate(base_model.layers):\n",
+    "       print(i, layer.name, \"-\", layer.trainable)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "import tensorflow.keras as K\n",
+    "\n",
+    "# this is the model we will train\n",
+    "model = K.models.Sequential()\n",
+    "model.add(K.layers.Lambda(lambda image: tf.image.resize(image, (224, 224))))\n",
+    "model.add(base_model)\n",
+    "model.add(K.layers.Flatten())\n",
+    "model.add(K.layers.BatchNormalization())\n",
+    "model.add(K.layers.Dense(256, activation='relu'))\n",
+    "model.add(K.layers.Dropout(0.5))\n",
+    "model.add(K.layers.BatchNormalization())\n",
+    "model.add(K.layers.Dense(128, activation='relu'))\n",
+    "model.add(K.layers.Dropout(0.5))\n",
+    "model.add(K.layers.BatchNormalization())\n",
+    "model.add(K.layers.Dense(64, activation='relu'))\n",
+    "model.add(K.layers.Dropout(0.5))\n",
+    "model.add(K.layers.BatchNormalization())\n",
+    "model.add(K.layers.Dense(133, activation='softmax')) # 3 is number of output"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "# we use SGD with a low learning rate\n",
+    "from tensorflow.keras.optimizers import SGD\n",
+    "model.compile(optimizer='rmsprop', loss='categorical_crossentropy', metrics=['accuracy']) # Define optimizer/LR"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "EPOCHS = 100 # number of cycle\n",
+    "\n",
+    "checkpoint = ModelCheckpoint('dog_vgg.h5',\n",
+    "                             monitor='val_loss',\n",
+    "                             mode='min',\n",
+    "                             save_best_only=True,\n",
+    "                             verbose=1)\n",
+    "\n",
+    "callbacks = [checkpoint]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "# start training\n",
+    "history = model.fit(train_ds, validation_data=val_ds,\n",
+    "          epochs=EPOCHS, callbacks=callbacks)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "# visualize the result (acc, val_acc, loss, val_loss)\n",
+    "\n",
+    "acc = history.history['accuracy']\n",
+    "val_acc = history.history['val_accuracy']\n",
+    "\n",
+    "loss = history.history['loss']\n",
+    "val_loss = history.history['val_loss']\n",
+    "\n",
+    "epochs_range = range(EPOCHS)\n",
+    "\n",
+    "plt.figure(figsize=(8, 8))\n",
+    "plt.subplot(1, 2, 1)\n",
+    "plt.plot(epochs_range, acc, label='Training Accuracy')\n",
+    "plt.plot(epochs_range, val_acc, label='Validation Accuracy')\n",
+    "plt.legend(loc='lower right')\n",
+    "plt.title('Training and Validation Accuracy')\n",
+    "\n",
+    "plt.subplot(1, 2, 2)\n",
+    "plt.plot(epochs_range, loss, label='Training Loss')\n",
+    "plt.plot(epochs_range, val_loss, label='Validation Loss')\n",
+    "plt.legend(loc='upper right')\n",
+    "plt.title('Training and Validation Loss')\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "import tensorflow as tf\n",
+    "\n",
+    "model = tf.keras.models.load_model('dog_vgg.h5')\n",
+    "converter = tf.lite.TFLiteConverter.from_keras_model(model)\n",
+    "tflite_model = converter.convert()\n",
+    "open(\"dog_vgg.tflite\", \"wb\").write(tflite_model)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "interpreter = tf.lite.Interpreter(model_path = \"dog_vgg.tflite\")\n",
+    "input_details = interpreter.get_input_details()\n",
+    "output_details = interpreter.get_output_details()\n",
+    "print(\"Input Shape:\", input_details[0]['shape'])\n",
+    "print(\"Input Type:\", input_details[0]['dtype'])\n",
+    "print(\"Output Shape:\", output_details[0]['shape'])\n",
+    "print(\"Output Type:\", output_details[0]['dtype'])"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 1
+}