Hey all,
I have a computer vision project. It detects car damages from an image. It’s a streamlit application.
I need to make a container on docker so I can deploy this app on azure.
So, I have a requirements.txt file, and cloned a git repo (this is the model): GitHub - facebookresearch/detectron2: Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
And I have two files - car_damage.pth, car_parts.pth that are the model weights.
This is my Dockerfile currently:
# Base image with CUDA support
FROM nvidia/cuda:12.6.0-cudnn-devel-ubuntu20.04
# Set working directory
WORKDIR /app
# Install system dependencies and Python
RUN apt-get update && \
apt-get install -y --no-install-recommends \
build-essential \
git \
curl \
wget \
libsm6 \
libxext6 \
libxrender-dev \
libglib2.0-0 \
ffmpeg \
&& rm -rf /var/lib/apt/lists/*
# Install Python dependencies
COPY requirements.txt ./
RUN pip install --upgrade pip && \
pip install -r requirements.txt
# Clone the detectron2 repository
RUN git clone https://github.com/facebookresearch/detectron2.git && \
cd detectron2 && \
pip install -e .
# Copy the application code into the container
COPY app_0.py ./
COPY car_damage.pth ./
COPY car_parts.pth ./
# Expose port for Streamlit
EXPOSE 8501
# Command to run Streamlit application
CMD ["streamlit", "run", "app_0.py", "--server.port", "8501", "--server.address", "0.0.0.0"]
Howevery, it’s not working. Can anyone help me please with this? I am new to docker… If you have done something similar to this , let me know .
Thanks a lot !