Update README.md

README.md

@@ -13,9 +13,6 @@ license: apache-2.0
 > [Learning and Vision Lab](http://lv-nus.org/), National University of Singapore  
 > Paper: [[Arxiv]](https://arxiv.org/abs/2312.05284)
 
-### Updates
-* 🚀 **December 11, 2023**: Release the training code, inference code and pre-trained models for **SlimSAM**. 
-
 ## Introduction
 
 <div align="center">
@@ -57,63 +54,10 @@ We conducted a comprehensive comparison encompassing performance, efficiency, an
   <img src="images/paper/compare_tab2.PNG" width="50%">
 </div>
 
-## Installation
-
-The code requires `python>=3.8`, as well as `pytorch>=1.7` and `torchvision>=0.8`. Please follow the instructions [here](https://pytorch.org/get-started/locally/) to install both PyTorch and TorchVision dependencies. Installing both PyTorch and TorchVision with CUDA support is strongly recommended.
-
-
-Install with
-
-```
-pip install -e .
-```
-
-The following optional dependencies are necessary for mask post-processing, saving masks in COCO format.
-
-```
-pip install opencv-python pycocotools matplotlib 
-```
-
-## Dataset
-We use the original SA-1B dataset in our code. See [here](https://ai.facebook.com/datasets/segment-anything/) for an overview of the datastet. The dataset can be downloaded [here](https://ai.facebook.com/datasets/segment-anything-downloads/).
-
-The download dataset should be saved as:
-
-```
-<train_data_root>/
-      sa_xxxxxxx.jpg
-      sa_xxxxxxx.json
-      ......
-<val_data_root>/
-      sa_xxxxxxx.jpg
-      sa_xxxxxxx.json
-      ......
-```
-
-
-To decode a mask in COCO RLE format into binary:
-
-``` python
-from pycocotools import mask as mask_utils
-mask = mask_utils.decode(annotation["segmentation"])
-```
-
-See [here](https://github.com/cocodataset/cocoapi/blob/master/PythonAPI/pycocotools/mask.py) for more instructions to manipulate masks stored in RLE format.
-
-
-## <a name="Models"></a>Model Checkpoints
-
-The base model of our method is available. To enhance collaboration with our dependency dectection algorithm, we have split the original image encoder's qkv layer into three distinct linear layers: q, k, and v.
-<div align="center">
-<img src="images/paper/split.PNG" width="70%">
-</div>
-
-
 
-Click the links below to download the checkpoints of orginal SAM-B.
 
-- `SAM-B`: [SAM-B model.](https://drive.google.com/file/d/1CtcyOm4h9bXgBF8DEVWn3N7g9-3r4Xzz/view?usp=sharing)
 
+## <a name="Models"></a>Model Using
 
 Fast state_dict loading for local uniform pruning SlimSAM-50 model:
 
@@ -130,38 +74,6 @@ masks = processor.image_processor.post_process_masks(outputs.pred_masks.cpu(), i
 scores = outputs.iou_scores
 ```
 
-
-## <a name="Inference"></a>Inference
-
-First download [SlimSAM-50 model](https://drive.google.com/file/d/1iCN9IW0Su0Ud_fOFoQUnTdkC3bFveMND/view?usp=sharing) or  [SlimSAM-77 model](https://drive.google.com/file/d/1L7LB6gHDzR-3D63pH9acD9E0Ul9_wMF-/view) for inference
-
-
-We provide detailed instructions in 'inference.py' on how to use a range of prompts, including 'point' and 'box' and 'everything', for inference purposes.
-
-```
-CUDA_VISIBLE_DEVICES=0 python inference.py
-```
-
-## <a name="Train"></a>Train
-
-First download a [SAM-B model](https://drive.google.com/file/d/1CtcyOm4h9bXgBF8DEVWn3N7g9-3r4Xzz/view?usp=sharing) into 'checkpoints/' as the base model. 
-
-### Step1: Embedding Pruning + Bottleneck Aligning ###
-The model after step1 is saved as 'checkpoints/vit_b_slim_step1_.pth'
-
-```
-CUDA_VISIBLE_DEVICES=0 python prune_distill_step1.py  --traindata_path <train_data_root> --valdata_path <val_data_root> --prune_ratio <pruning ratio> --epochs <training epochs>
-```
-
-### Step2: Bottleneck Pruning + Embedding Aligning ###
-The model after step2 is saved as 'checkpoints/vit_b_slim_step2_.pth'
-
-```
-CUDA_VISIBLE_DEVICES=0 python prune_distill_step2.py  --traindata_path <train_data_root> --valdata_path <val_data_root> --prune_ratio <pruning ratio> --epochs <training epochs> --model_path 'checkpoints/vit_b_slim_step1_.pth' 
-```
-
-You can adjust the training settings to meet your specific requirements. While our method demonstrates impressive performance with just 10,000 training data, incorporating additional training data will further enhance the model's effectiveness
-
 ## BibTex of our SlimSAM
 If you use SlimSAM in your research, please use the following BibTeX entry. Thank you!