Update app.py

app.py

@@ -45,7 +45,7 @@ api.upload_folder(
 #.commit(commit_message="clipseg uploaded...")
 #    with open("file.txt", "w+") as f:
 #        f.write(json.dumps({"hey": 8}))
-        
+
 
 auth_token = os.environ.get("API_TOKEN") or True
 
@@ -149,11 +149,11 @@ with image_blocks as demo:
                   fill="none"
                   xmlns="http://www.w3.org/2000/svg"
                 >
-                  <rect width="23" height="23" fill="white"></rect>
-                  <rect y="69" width="23" height="23" fill="white"></rect>
+                  <rect width="23" height="23" fill="#AEAEAE"></rect>
+                  <rect y="69" width="23" height="23" fill="black"></rect>
                   <rect x="23" width="23" height="23" fill="#AEAEAE"></rect>
                   <rect x="23" y="69" width="23" height="23" fill="#AEAEAE"></rect>
-                  <rect x="46" width="23" height="23" fill="white"></rect>
+                  <rect x="46" width="23" height="23" fill="#D9D9D9"></rect>
                   <rect x="46" y="69" width="23" height="23" fill="white"></rect>
                   <rect x="69" width="23" height="23" fill="black"></rect>
                   <rect x="69" y="69" width="23" height="23" fill="black"></rect>
@@ -180,7 +180,7 @@ with image_blocks as demo:
                 </h1>
               </div>
               <p style="margin-bottom: 10px; font-size: 94%">
-                Inpaint Stable Diffusion by either drawing a mask or typing what to replace
+                Inpaint Stable Diffusion by either drawing a mask or typing what to replace & what to keep !!!
               </p>
             </div>
         """
@@ -205,6 +205,87 @@ with image_blocks as demo:
         btn.click(fn=predict, inputs=[radio, image, word_mask, prompt], outputs=result)
     gr.HTML(
             """
+            # Image Segmentation Using Text and Image Prompts
+This repository contains the code used in the paper ["Image Segmentation Using Text and Image Prompts"](https://arxiv.org/abs/2112.10003).
+
+**The Paper has been accepted to CVPR 2022!**
+
+<img src="overview.png" alt="drawing" height="200em"/>
+
+The systems allows to create segmentation models without training based on:
+- An arbitrary text query
+- Or an image with a mask highlighting stuff or an object.
+
+### Quick Start
+
+In the `Quickstart.ipynb` notebook we provide the code for using a pre-trained CLIPSeg model. If you run the notebook locally, make sure you downloaded the `rd64-uni.pth` weights, either manually or via git lfs extension.
+It can also be used interactively using [MyBinder](https://mybinder.org/v2/gh/timojl/clipseg/HEAD?labpath=Quickstart.ipynb)
+(please note that the VM does not use a GPU, thus inference takes a few seconds).
+
+
+### Dependencies
+This code base depends on pytorch, torchvision and clip (`pip install git+https://github.com/openai/CLIP.git`).
+Additional dependencies are hidden for double blind review.
+
+
+### Datasets
+
+* `PhraseCut` and `PhraseCutPlus`: Referring expression dataset
+* `PFEPascalWrapper`: Wrapper class for PFENet's Pascal-5i implementation
+* `PascalZeroShot`: Wrapper class for PascalZeroShot
+* `COCOWrapper`: Wrapper class for COCO.
+
+### Models
+
+* `CLIPDensePredT`: CLIPSeg model with transformer-based decoder.
+* `ViTDensePredT`: CLIPSeg model with transformer-based decoder.
+
+### Third Party Dependencies
+For some of the datasets third party dependencies are required. Run the following commands in the `third_party` folder.  
+```bash
+git clone https://github.com/cvlab-yonsei/JoEm
+git clone https://github.com/Jia-Research-Lab/PFENet.git
+git clone https://github.com/ChenyunWu/PhraseCutDataset.git
+git clone https://github.com/juhongm999/hsnet.git
+```
+
+### Weights
+
+The MIT license does not apply to these weights.
+
+- [CLIPSeg-D64](https://github.com/timojl/clipseg/raw/master/weights/rd64-uni.pth) (4.1MB, without CLIP weights)
+- [CLIPSeg-D16](https://github.com/timojl/clipseg/raw/master/weights/rd16-uni.pth) (1.1MB, without CLIP weights)
+
+### Training and Evaluation
+
+To train use the `training.py` script with experiment file and experiment id parameters. E.g. `python training.py phrasecut.yaml 0` will train the first phrasecut experiment which is defined by the `configuration` and first `individual_configurations` parameters. Model weights will be written in `logs/`.
+
+For evaluation use `score.py`. E.g. `python score.py phrasecut.yaml 0 0` will train the first phrasecut experiment of `test_configuration` and the first configuration in `individual_configurations`.
+
+
+### Usage of PFENet Wrappers
+
+In order to use the dataset and model wrappers for PFENet, the PFENet repository needs to be cloned to the root folder.
+`git clone https://github.com/Jia-Research-Lab/PFENet.git `
+
+
+### License
+
+The source code files in this repository (excluding model weights) are released under MIT license.
+
+### Citation
+```
+@InProceedings{lueddecke22_cvpr,
+    author    = {L\"uddecke, Timo and Ecker, Alexander},
+    title     = {Image Segmentation Using Text and Image Prompts},
+    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
+    month     = {June},
+    year      = {2022},
+    pages     = {7086-7096}
+}
+
+```
+
                 <div class="footer">
                     <p>Model by <a href="https://huggingface.co/CompVis" style="text-decoration: underline;" target="_blank">CompVis</a> and <a href="https://huggingface.co/stabilityai" style="text-decoration: underline;" target="_blank">Stability AI</a> - Inpainting by <a href="https://github.com/" style="text-decoration: underline;" target="_blank">NightFury</a> using clipseg[model] with bit modification - Gradio Demo on 🤗 Hugging Face
                     </p>