Update Detection Class for TensorFlow 2.x and NumPy Compatibility

deep_sort/detection.py

@@ -27,7 +27,7 @@ class Detection(object):
     """
 
     def __init__(self, tlwh, confidence, feature):
-        self.tlwh = np.asarray(tlwh, dtype=np.float)
+        self.tlwh = np.asarray(tlwh, dtype=float)
         self.confidence = float(confidence)
         self.feature = np.asarray(feature, dtype=np.float32)
 

deep_sort/linear_assignment.py

@@ -1,10 +1,10 @@
 # vim: expandtab:ts=4:sw=4
 from __future__ import absolute_import
 import numpy as np
-from sklearn.utils.linear_assignment_ import linear_assignment
+from scipy.optimize  import linear_sum_assignment 
 from . import kalman_filter
 
-
+     
 INFTY_COST = 1e+5
 
 
@@ -55,8 +55,11 @@ def min_cost_matching(
     cost_matrix = distance_metric(
         tracks, detections, track_indices, detection_indices)
     cost_matrix[cost_matrix > max_distance] = max_distance + 1e-5
-    indices = linear_assignment(cost_matrix)
 
+    #use linear_sum_assignment from scipy
+    row_indices, col_indices = linear_sum_assignment(cost_matrix)
+    indices = np.array(list(zip(row_indices, col_indices)))
+
     matches, unmatched_tracks, unmatched_detections = [], [], []
     for col, detection_idx in enumerate(detection_indices):
         if col not in indices[:, 1]:

tools/generate_detections.py

@@ -5,6 +5,8 @@
 import numpy as np
 import cv2
 import tensorflow as tf
+tf.compat.v1.disable_eager_execution()  # TF 2.x compatible
+
 
 
 def _run_in_batches(f, data_dict, out, batch_size):
@@ -55,7 +57,7 @@ def extract_image_patch(image, bbox, patch_shape):
 
     # convert to top left, bottom right
     bbox[2:] += bbox[:2]
-    bbox = bbox.astype(np.int)
+    bbox = bbox.astype(int)
 
     # clip at image boundaries
     bbox[:2] = np.maximum(0, bbox[:2])
@@ -70,23 +72,33 @@ def extract_image_patch(image, bbox, patch_shape):
 
 class ImageEncoder(object):
 
+
+
     def __init__(self, checkpoint_filename, input_name="images",
                  output_name="features"):
-        self.session = tf.Session()
-        with tf.gfile.GFile(checkpoint_filename, "rb") as file_handle:
-            graph_def = tf.GraphDef()
+        # Use TensorFlow 2.x compatible session
+        self.session = tf.compat.v1.Session()
+
+        # Load the graph definition file
+        with tf.io.gfile.GFile(checkpoint_filename, "rb") as file_handle:
+            graph_def = tf.compat.v1.GraphDef()
             graph_def.ParseFromString(file_handle.read())
+
+        # Import the graph and get the input and output tensors
         tf.import_graph_def(graph_def, name="net")
-        self.input_var = tf.get_default_graph().get_tensor_by_name(
+        self.input_var = tf.compat.v1.get_default_graph().get_tensor_by_name(
             "net/%s:0" % input_name)
-        self.output_var = tf.get_default_graph().get_tensor_by_name(
+        self.output_var = tf.compat.v1.get_default_graph().get_tensor_by_name(
             "net/%s:0" % output_name)
 
+        # Validate the tensor shapes
         assert len(self.output_var.get_shape()) == 2
         assert len(self.input_var.get_shape()) == 4
         self.feature_dim = self.output_var.get_shape().as_list()[-1]
         self.image_shape = self.input_var.get_shape().as_list()[1:]
 
+
+
     def __call__(self, data_x, batch_size=32):
         out = np.zeros((len(data_x), self.feature_dim), np.float32)
         _run_in_batches(