From 7e7ba356b49c2757de0040acd8f177dfa68fa63e Mon Sep 17 00:00:00 2001 From: Satyam Rastogi Date: Mon, 15 Dec 2025 22:20:04 +0530 Subject: [PATCH] update README with comprehensive requirements and dependencies --- README.md | 22 +++++++++++++++++++--- 1 file changed, 19 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index f70c431..a86d792 100644 --- a/README.md +++ b/README.md @@ -37,9 +37,16 @@ To run these notebooks, you'll need: - Pillow - NumPy - OpenCV-Python -- Moondream model dependencies - Matplotlib - Scikit-image +- Moondream (for Moondream models) +- SAM (Segment Anything) and Grounding DINO (for segmentation tasks) +- Hugging Face Accelerate (for optimized inference) +- Requests +- Json (standard library, but used extensively) +- tqdm (for progress bars) +- BitsAndBytes (for quantized models) +- SentencePiece (for tokenization, if needed) ## Setup @@ -47,9 +54,14 @@ To run these notebooks, you'll need: 2. Install required dependencies: ```bash -pip install torch torchvision +pip install torch torchvision torchaudio pip install transformers pillow numpy opencv-python matplotlib scikit-image -pip install moondream +pip install moondream jupyter +pip install accelerate bitsandbytes sentencepiece +pip install supervision # For visualization and annotations +pip install segment-anything # For SAM model +pip install groundingdino-py # For Grounding DINO +pip install huggingface_hub ``` 3. Launch Jupyter: @@ -81,10 +93,14 @@ Each notebook serves a specific purpose in the image annotation pipeline: ## Dependencies - [Moondream](https://github.com/vikhyat/moondream) - Efficient vision-language model +- [Segment Anything (SAM)](https://segment-anything.com/) - Advanced segmentation model +- [Grounding DINO](https://github.com/IDEA-Research/GroundingDINO) - Open-set object detection - PyTorch - Deep learning framework - OpenCV - Computer vision operations - COCO API - Annotation format handling - Transformers - Hugging Face library for model processing +- Supervision - Utilities for computer vision workflows +- Accelerate - Optimization library for PyTorch models ## Notes