[feat] add .idea files, update README.md

.idea/LISA_REFACTOR.iml

@@ -0,0 +1,15 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+  <component name="PyDocumentationSettings">
+    <option name="format" value="GOOGLE" />
+    <option name="myDocStringFormat" value="Google" />
+  </component>
+  <component name="SonarLintModuleSettings">
+    <option name="uniqueId" value="875f314e-5ed1-4106-8048-37fa08d9c6e3" />
+  </component>
+</module>

.idea/inspectionProfiles/Project_Default.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <profile version="1.0">
+    <option name="myName" value="Project Default" />
+    <inspection_tool class="Eslint" enabled="true" level="WARNING" enabled_by_default="true" />
+  </profile>
+</component>

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/LISA_REFACTOR.iml" filepath="$PROJECT_DIR$/.idea/LISA_REFACTOR.iml" />
+    </modules>
+  </component>
+</project>

README.md

@@ -1,3 +1,14 @@
+---
+title: Lisa On Gpu
+emoji: 📊
+colorFrom: yellow
+colorTo: red
+sdk: docker
+pinned: false
+---
+
+(Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference)
+
 [![Gradio](https://img.shields.io/badge/Gradio-Online%20Demo-blue)](http://103.170.5.190:7860/)
 [![Open in OpenXLab](https://cdn-static.openxlab.org.cn/app-center/openxlab_app.svg)](https://openxlab.org.cn/apps/detail/openxlab-app/LISA)
 
@@ -7,7 +18,7 @@
 
 <font size=7><div align='center' > <a href=https://arxiv.org/pdf/2308.00692.pdf>**Paper**</a> | <a href="https://huggingface.co/xinlai">**Models**</a> | [**Training**](#training) | [**Inference**](#inference) | [**Local Deployment**](#deployment) | [**Dataset**](#dataset) | <a href="http://103.170.5.190:7860/">**Online Demo**</a></div></font>
 
-<!-- <p align="center"> <img src="imgs/teaser.jpg" width="100%"> </p> -->
+<!-- <p align="center"> <img src="resources/imgs/teaser.jpg" width="100%"> </p> -->
 
 <table class="center">
 <tr>
@@ -17,9 +28,9 @@
   <td style="text-align:center;"><b>Output</b></td>
 </tr>
 <tr>
-  <td><img src="imgs/obama.jpg"></td>
+  <td><img src="resources/imgs/obama.jpg"></td>
   <td><img src="vis_output/obama.jpg"></td>
-  <td><img src="imgs/trump.jpg"></td>              
+  <td><img src="resources/imgs/trump.jpg"></td>              
   <td><img src="vis_output/trump.jpg"></td>
 </tr>
 <tr>
@@ -30,9 +41,9 @@
 </tr>
 
 <tr>
-  <td><img src="imgs/stand_higher.jpg"></td>
+  <td><img src="resources/imgs/stand_higher.jpg"></td>
   <td><img src="vis_output/stand_higher.jpg"></td>
-  <td><img src="imgs/camera_lens.jpg"></td>              
+  <td><img src="resources/imgs/camera_lens.jpg"></td>              
   <td><img src="vis_output/camera_lens.jpg"></td>
 </tr>
 <tr>
@@ -43,9 +54,9 @@
 </tr>
 
 <tr>
-  <td><img src="imgs/dog_with_horn.jpg"></td>
+  <td><img src="resources/imgs/dog_with_horn.jpg"></td>
   <td><img src="vis_output/dog_with_horn.jpg"></td>
-  <td><img src="imgs/wash_hands.jpg"></td>              
+  <td><img src="resources/imgs/wash_hands.jpg"></td>              
   <td><img src="vis_output/wash_hands.jpg"></td>
 </tr>
 <tr>
@@ -56,9 +67,9 @@
 </tr>
 
 <tr>
-  <td><img src="imgs/jackma.jpg"></td>
+  <td><img src="resources/imgs/jackma.jpg"></td>
   <td><img src="vis_output/jackma.jpg"></td>
-  <td><img src="imgs/blackpink.jpg"></td>              
+  <td><img src="resources/imgs/blackpink.jpg"></td>              
   <td><img src="vis_output/blackpink.jpg"></td>
 </tr>
 <tr>
@@ -69,7 +80,7 @@
 </tr>
 </table>
 
-<p align="center"> <img src="imgs/fig_overview.jpg" width="100%"> </p>
+<p align="center"> <img src="resources/imgs/fig_overview.jpg" width="100%"> </p>
 
 ## News
 - [x] [2023.8.30] Release three new models [LISA-7B-v1](https://huggingface.co/xinlai/LISA-7B-v1), [LISA-7B-v1-explanatory](https://huggingface.co/xinlai/LISA-7B-v1-explanatory), and [LISA-13B-llama2-v1-explanatory](https://huggingface.co/xinlai/LISA-13B-llama2-v1-explanatory). Welcome to check them out!
@@ -103,7 +114,7 @@ For more details, please refer to the [paper](https://arxiv.org/abs/2308.00692).
 **LISA** also demonstrates robust zero-shot capability when trained exclusively on reasoning-free datasets. In addition, fine-tuning the model with merely 239 reasoning segmentation image-instruction pairs results in further performance enhancement.
 
 ## Experimental results
-<p align="center"> <img src="imgs/table1.jpg" width="80%"> </p>
+<p align="center"> <img src="resources/imgs/table1.jpg" width="80%"> </p>
 
 ## Installation
 ```
@@ -131,44 +142,44 @@ Download them from the above links, and organize them as follows.
 
 ```
 ├── dataset
-│   ├── ade20k
-│   │   ├── annotations
-│   │   └── images
-│   ├── coco
-│   │   └── train2017
-│   │       ├── 000000000009.jpg
-│   │       └── ...
-│   ├── cocostuff
-│   │   └── train2017
-│   │       ├── 000000000009.png
-│   │       └── ...
-│   ├── llava_dataset
-│   │   └── llava_instruct_150k.json
-│   ├── mapillary
-│   │   ├── config_v2.0.json
-│   │   ├── testing
-│   │   ├── training
-│   │   └── validation
-│   ├── reason_seg
-│   │   └── ReasonSeg
-│   │       ├── train
-│   │       ├── val
-│   │       └── explanatory
-│   ├── refer_seg
-│   │   ├── images
-│   │   |   ├── saiapr_tc-12 
-│   │   |   └── mscoco
-│   │   |       └── images
-│   │   |           └── train2014
-│   │   ├── refclef
-│   │   ├── refcoco
-│   │   ├── refcoco+
-│   │   └── refcocog
-│   └── vlpart
-│       ├── paco
+│         ├── ade20k
+│         │         ├── annotations
+│         │         └── images
+│         ├── coco
+│         │         └── train2017
+│         │             ├── 000000000009.jpg
+│         │             └── ...
+│         ├── cocostuff
+│         │         └── train2017
+│         │             ├── 000000000009.png
+│         │             └── ...
+│         ├── llava_dataset
+│         │         └── llava_instruct_150k.json
+│         ├── mapillary
+│         │         ├── config_v2.0.json
+│         │         ├── testing
+│         │         ├── training
+│         │         └── validation
+│         ├── reason_seg
+│         │         └── ReasonSeg
+│         │             ├── train
+│         │             ├── val
+│         │             └── explanatory
+│         ├── refer_seg
+│         │         ├── images
+│         │         |   ├── saiapr_tc-12 
+│         │         |   └── mscoco
+│         │         |       └── images
+│         │         |           └── train2014
+│         │         ├── refclef
+│         │         ├── refcoco
+│         │         ├── refcoco+
+│         │         └── refcocog
+│         └── vlpart
+│             ├── paco
 │       │   └── annotations
-│       └── pascal_part
-│           ├── train.json
+│             └── pascal_part
+│                 ├── train.json
 │           └── VOCdevkit
 ```
 
@@ -253,7 +264,7 @@ After that, input the text prompt and then the image path. For example，
 - Please input the image path: imgs/example2.jpg
 ```
 The results should be like:
-<p align="center"> <img src="imgs/example1.jpg" width="22%"> <img src="vis_output/example1_masked_img_0.jpg" width="22%"> <img src="imgs/example2.jpg" width="25%"> <img src="vis_output/example2_masked_img_0.jpg" width="25%"> </p>
+<p align="center"> <img src="resources/imgs/example1.jpg" width="22%"> <img src="vis_output/example1_masked_img_0.jpg" width="22%"> <img src="resources/imgs/example2.jpg" width="25%"> <img src="vis_output/example2_masked_img_0.jpg" width="25%"> </p>
 
 ## Deployment
 ```