Merge pull request #3 from anxiangsir/dev_anxiang

docs(readme): update dockerfile

Author: anxiangsir

Encoder_Eval/README.md

@@ -26,14 +26,29 @@ This repository provides a unified evaluation framework for benchmarking **video
 
 ## 🔧 Setup
 
+
+### 1. Optional: Using Dockerfile for Environment Setup
+```bash
+docker build -t llava_vit_eval:25.09 .
+```
+### 2. Or Load Docker Image
 ```bash
-# Clone the repo
-git clone git@github.com:FeilongTangmonash/Encoder_Eval.git
-cd Encoder_Eval
+docker load -i /vlm/xiangan/docker_images/llava_vit_eval_tag_25.09.tar
+docker tag <image_id> llava_vit_eval:25.09
+```
 
-# Install dependencies
-pip install -r requirements.txt
+### 3. Run
+```
+# Run container with -w to set working directory directly to the mounted volume
+docker run -it --gpus all \
+    --ipc host --net host --privileged --cap-add IPC_LOCK \
+    --ulimit memlock=-1 --ulimit stack=67108864 --rm \
+    -v "$(cd .. && pwd)":/workspace/LLaVA-ViT \
+    -w /workspace/LLaVA-ViT/Encoder_Eval \
+    --name "llava_vit_eval_container" \
+    llava_vit_eval:25.09 /bin/bash
 ```
+
 ## 🧱 code structure
 
 <pre>

Encoder_Eval/dockerfile

@@ -0,0 +1,19 @@
+FROM pytorch/pytorch:2.7.0-cuda11.8-cudnn9-runtime
+
+# Set up environment variables (optional, but often recommended)
+ENV DEBIAN_FRONTEND=noninteractive
+
+# Install Python packages
+RUN pip install --no-cache-dir --extra-index-url https://pypi.nvidia.com --upgrade nvidia-dali-cuda110 \
+    && pip install --no-cache-dir decord==0.6.0 \
+    && pip install --no-cache-dir timm \
+    && pip install --no-cache-dir transformers==4.52.4
+
+# (Optional) Set working directory
+WORKDIR /workspace
+
+# (Optional) Copy your code into the container
+# COPY . /workspace
+
+# (Optional) Set entrypoint or CMD
+# CMD ["python", "your_script.py"]