Update README.md

README.md

@@ -27,16 +27,18 @@ Zhaopeng Gu, Bingke Zhu, Guibo Zhu, Yingying Chen, Ming Tang, Jinqiao Wang
 
 * <a href='#introduction'>1. Introduction</a>
 * <a href='#environment'>2. Running AnomalyGPT Demo</a>
-    * <a href='#install_environment'>2.1. Environment Installation</a>
-    * <a href='#download_imagebind_model'>2.2. Prepare ImageBind Checkpoint</a>
-    * <a href='#download_vicuna_model'>2.3. Prepare Vicuna Checkpoint</a>
-    * <a href='#download_anomalygpt'>2.4. Prepare Delta Weights of AnomalyGPT</a>
-    * <a href='#running_demo'>2.5. Deploying Demo</a>
+    * <a href='#install_environment'>2.1 Environment Installation</a>
+    * <a href='#download_imagebind_model'>2.2 Prepare ImageBind Checkpoint</a>
+    * <a href='#download_vicuna_model'>2.3 Prepare Vicuna Checkpoint</a>
+    * <a href='#download_anomalygpt'>2.4 Prepare Delta Weights of AnomalyGPT</a>
+    * <a href='#running_demo'>2.5 Deploying Demo</a>
 * <a href='#train_anomalygpt'>3. Train Your Own AnomalyGPT</a>
-    * <a href='#data_preparation'>3.1. Data Preparation</a>
-    * <a href='#training_configurations'>3.2. Training Configurations</a>
-    * <a href='#model_training'>3.3. Training AnoamlyGPT</a>
-<!-- * <a href='#results'>4. Results</a> -->
+    * <a href='#data_preparation'>3.1 Data Preparation</a>
+    * <a href='#training_configurations'>3.2 Training Configurations</a>
+    * <a href='#model_training'>3.3 Training AnoamlyGPT</a>
+
+* <a href='#examples'>4. Examples</a>
+<!-- * <a href='#results'>5. Results</a> -->
 * <a href='#license'>License</a>
 * <a href='#citation'>Citation</a>
 * <a href='#acknowledgments'>Acknowledgments</a>
@@ -66,7 +68,7 @@ We leverage a pre-trained image encoder and a Large Language Model (LLM) to alig
 
 <span id='install_environment'/>
 
-#### 2.1. Environment Installation
+#### 2.1 Environment Installation
 
 Clone the repository locally:
 
@@ -82,19 +84,19 @@ pip install -r requirements.txt
 
 <span id='download_imagebind_model'/>
 
-#### 2.2. Prepare ImageBind Checkpoint:
+#### 2.2 Prepare ImageBind Checkpoint:
 
 You can download the pre-trained ImageBind model using [this link](https://dl.fbaipublicfiles.com/imagebind/imagebind_huge.pth). After downloading, put the downloaded file (imagebind_huge.pth) in [[./pretrained_ckpt/imagebind_ckpt/]](./pretrained_ckpt/imagebind_ckpt/) directory. 
 
 <span id='download_vicuna_model'/>
 
-#### 2.3. Prepare Vicuna Checkpoint:
+#### 2.3 Prepare Vicuna Checkpoint:
 
 To prepare the pre-trained Vicuna model, please follow the instructions provided [[here]](./pretrained_ckpt#1-prepare-vicuna-checkpoint).
 
 <span id='download_anomalygpt'/>
 
-#### 2.4. Prepare Delta Weights of AnomalyGPT:
+#### 2.4 Prepare Delta Weights of AnomalyGPT:
 
 We use the pre-trained parameters from [PandaGPT](https://github.com/yxuansu/PandaGPT) to initialize our model. You can get the weights of PandaGPT trained with different strategies in the table below. In our experiments and online demo, we use the Vicuna-7B and `openllmplayground/pandagpt_7b_max_len_1024` due to the limitation of computation resource. Better results are expected if switching to Vicuna-13B.
 
@@ -121,7 +123,7 @@ In our [online demo](), we use the supervised setting as our default model to at
 
 <span id='running_demo'/>
 
-#### 2.5. Deploying Demo
+#### 2.5 Deploying Demo
 
 Upon completion of previous steps, you can run the demo locally as
 ```bash
@@ -139,7 +141,7 @@ python web_demo.py
 
 <span id='data_preparation'/>
 
-#### 3.1. Data Preparation:
+#### 3.1 Data Preparation:
 
 You can download MVTec-AD dataset from [[this link]](https://www.mvtec.com/company/research/datasets/mvtec-ad/downloads) and VisA from [[this link]](https://github.com/amazon-science/spot-diff). You can also download pre-training data of PandaGPT from [[here]](https://huggingface.co/datasets/openllmplayground/pandagpt_visual_instruction_dataset/tree/main). After downloading, put the data in the [[./data]](./data/) directory.
 
@@ -189,7 +191,7 @@ The table below show the training hyperparameters used in our experiments. The h
 
 <span id='model_training'/>
 
-#### 3.3. Training AnomalyGPT
+#### 3.3 Training AnomalyGPT
 
 To train AnomalyGPT on MVTec-AD dataset, please run the following commands:
 ```yaml
@@ -208,6 +210,23 @@ The key arguments of the training script are as follows:
 
 Note that the epoch number can be set in the `epochs` argument at [./code/config/openllama_peft.yaml](./code/config/openllama_peft.yaml) file and the learning rate can be set in  [./code/dsconfig/openllama_peft_stage_1.json](./code/dsconfig/openllama_peft_stage_1.json)
 
+****
+
+<span id='examples'/>
+
+### 4. Examples
+
+![](./images/demo_1.png)
+****
+![](./images/demo_5.png)
+****
+![](./images/demo_2.png)
+****
+![](./images/demo_4.png)
+****
+![](./images/demo_3.png)
+
+
 <!-- ****
 
 <span id='results'/>