Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
PyTorch implementation of DeepLabV3, trained on the Cityscapes dataset.
| Date | Stars |
|---|---|
| 2026-07-24 | 816 |
| 2026-07-25 | 816 |
| 2026-07-28 | 816 |
| 2026-07-30 | 816 |
| 2026-08-06 | 816 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# deeplabv3
PyTorch implementation of [DeepLabV3](https://arxiv.org/abs/1706.05587), trained on the [Cityscapes](https://www.cityscapes-dataset.com/) dataset.
- [Youtube video](https://youtu.be/9e2x4dDRB-k) of results:
[](https://youtu.be/9e2x4dDRB-k)
## Index
- [Using a VM on Paperspace](#paperspace)
- [Pretrained model](#pretrained-model)
- [Training a model on Cityscapes](#train-model-on-cityscapes)
- [Evaluation](#evaluation)
- [Visualization](#visualization)
- [Documentation of remaining code](#documentation-of-remaining-code)
****
****
******
## Paperspace:
To train models and to run pretrained models (with small batch sizes), you can use an Ubuntu 16.04 P4000 VM with 250 GB SSD on Paperspace. Below I have listed what I needed to do in order to get started, and some things I found useful.
- Install docker-ce:
- - $ curl -fsSL https://download.docker.com/linux/ubuntu/gpg | sudo apt-key add -
- - $ sudo add-apt-repository "deb [arch=amd64] https://download.docker.com/linux/ubuntu $(lsb_release -cs) stable"
- - $ sudo apt-get update
- - $ sudo apt-get install -y docker-ce
- Install CUDA drivers:
- - $ CUDA_REPO_PKG=cuda-repo-ubuntu1604_9.1.85-1_amd64.deb
- - $ wget -O /tmp/${CUDA_REPO_PKG} http://developer.download.nvidia.com/compute/cuda/repos/ubuntu1604/x86_64/${CUDA_REPO_PKG}
- - $ sudo dpkg -i /tmp/${CUDA_REPO_PKG}
- - $ sudo apt-key adv --fetch-keys http://developer.download.nvidia.com/compute/cuda/repos/ubuntu1604/x86_64/7fa2af80.pub
- - $ rm -f /tmp/${CUDA_REPO_PKG}
- - $ sudo apt-get update
- - $ sudo apt-get install cuda-drivers
- - Reboot the VM.
- Install nvidia-docker:
- - $ wget -P /tmp https://github.com/NVIDIA/nvidia-docker/releases/download/v1.0.1/nvidia-docker_1.0.1-1_amd64.deb
- - $ sudo dpkg -i /tmp/nvidia-docker*.deb && rm /tmp/nvidia-docker*.deb
- - $ sudo nvidia-docker run --rm nvidia/cuda nvidia-smi
- Download the PyTorch 0.4 docker image:
- - $ sudo docker pull pytorch/pytorch:0.4_cuda9_cudnn7
- Create start_docker_image.sh containing:
```
#!/bin/bash
# DEFAULT VALUES
GPUIDS="0"
NAME="paperspace_GPU"
NV_GPU="$GPUIDS" nvidia-docker run -it --rm \
-p 5584:5584 \
--name "$NAME""$GPUIDS" \
-v /home/paperspace:/root/ \
pytorch/pytorch:0.4_cuda9_cudnn7 bash
```
- Inside the image, /root/ will now be mapped to /home/paperspace (i.e., $ cd -- takes you to the regular home folder).
- To start the image:
- - $ sudo sh start_docker_image.sh
- To commit changes to the image:
- - Open a new terminal window.
- - $ sudo docker commit paperspace_GPU0 pytorch/pytorch:0.4_cuda9_cudnn7
- To stop the image when it’s running:
- - $ sudo docker stop paperspace_GPU0
- To exit the image without killing running code:
- - Ctrl + P + Q
- To get back into a running image:
- - $ sudo docker attach paperspace_GPU0
- To open more than one terminal window at the same time:
- - $ sudo docker exec -it paperspace_GPU0 bash
- To install the needed software inside the docker image:
- - $ apt-get update
- - $ apt-get install nano
- - $ apt-get install sudo
- - $ apt-get install wget
- - $ sudo apt install unzip
- - $ sudo apt-get install libopencv-dev
- - $ pip install opencv-python
- - $ python -mpip install matplotlib
- - Commit changes to the image (otherwise, the installed packages will be removed at exit!)
- Do the following outside of the docker image:
- - $ --
- - $ git clone https://github.com/fregu856/deeplabv3.git
- - Download the Cityscapes dataset:
- - - Register on the [website](https://www.cityscapes-dataset.com/).
- - - $ wget --keep-session-cookies --save-cookies=cookies.txt --post-data 'username=XXXXX&password=YYYYY&submit=Login' https://www.cityscapes-dataset.com/login/ *(where you replace XXXXX with your username, and YYYYY with your password)*
- - - $ wget --load-cookies cookies.txt --content-disposition https://www.cityscapes-dataset.com/file-handling/?packageID=1
- - - $ wget --load-cookies Excerpt of 10,223 characters
Read on GitHub
57
Erjan K · Netherlands
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:c3f28b57f5865780, topic:deep-learning, topic:pytorch
matched fp:c3f28b57f5865780, topic:computer-vision
matched fp:c3f28b57f5865780, topic:autonomous-driving