Skip to content

Commit

Permalink
docs: update args description
Browse files Browse the repository at this point in the history
  • Loading branch information
sokovninn committed Feb 20, 2024
1 parent f00ee4c commit 8cb475e
Show file tree
Hide file tree
Showing 2 changed files with 5 additions and 1 deletion.
3 changes: 2 additions & 1 deletion README.md
Original file line number Diff line number Diff line change
Expand Up @@ -116,6 +116,7 @@ datadreamer --save_dir <directory> --class_names <objects> --prompts_number <num
- `--image_tester_patience`: Patience level for image tester. Default is 1.
- `--lm_quantization`: Quantization to use for Mistral language model. Choose between `none` and `4bit`. Default is `none`.
- `--batch_size_prompt`: Batch size for prompt generation. Default is 64.
- `--batch_size_image`: Batch size for image generation. Default is 1.
- `--device`: Choose between `cuda` and `cpu`. Default is cuda.
- `--seed`: Set a random seed for image and prompt generation. Default is 42.

Expand All @@ -130,7 +131,7 @@ datadreamer --save_dir <directory> --class_names <objects> --prompts_number <num
| | Simple random generator | Joins randomly chosen object names |
| Image Generation | [SDXL-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0) | Slow and accurate (1024x1024 images) |
| | [SDXL-Turbo](https://huggingface.co/stabilityai/sdxl-turbo) | Fast and less accurate (512x512 images) |
| Image Annotation | [OWLv2](https://huggingface.co/google/owlv2-large-patch14-ensemble) | Open-Vocabulary object detector |
| Image Annotation | [OWLv2](https://huggingface.co/google/owlv2-base-patch16-ensemble) | Open-Vocabulary object detector |

<a name="example"></a>

Expand Down
3 changes: 3 additions & 0 deletions examples/generate_dataset_and_train_yolo.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -84,6 +84,9 @@
"- `--enhance_class_names`: Enhance class names with synonyms. Default is False.\n",
"- `--use_image_tester`: Use image tester for image generation. Default is False. Image tester is a model that checks if the generated image contains the desired object.\n",
"- `--image_tester_patience`: Patience level for image tester. Default is 1. Number of images to run through the image tester before giving up.\n",
"- `--lm_quantization`: Quantization to use for Mistral language model. Choose between `none` and `4bit`. Default is `none`.\n",
"- `--batch_size_prompt`: Batch size for prompt generation. Default is 64. Increase for faster prompt generation, decrease if there is no enough GPU memory.\n",
"- `--batch_size_image`: Batch size for image generation. Default is 1. Increase for faster image generation.\n",
"- `--seed`: Set a random seed for image and prompt generation. Default is 42.\n"
]
},
Expand Down

0 comments on commit 8cb475e

Please sign in to comment.