A novel deep neural network architecture which allows it to learn without any significant increase in number of parameters. The network uses only 11.5 million parameters and 21.2 GFLOPs for processing an image of resolution 3x640x360.
| GPU | IXUCA SDK | Release |
|---|---|---|
| BI-V100 | 2.2.0 | 22.09 |
Go to visit COCO official website, then select the COCO dataset you want to download.
Take coco2017 dataset as an example, specify /path/to/coco2017 to your COCO path in later training process, the
unzipped dataset path structure sholud look like:
coco2017
├── annotations
│ ├── instances_train2017.json
│ ├── instances_val2017.json
│ └── ...
├── train2017
│ ├── 000000000009.jpg
│ ├── 000000000025.jpg
│ └── ...
├── val2017
│ ├── 000000000139.jpg
│ ├── 000000000285.jpg
│ └── ...
├── train2017.txt
├── val2017.txt
└── ...pip3 install 'scipy' 'matplotlib' 'pycocotools' 'opencv-python' 'easydict' 'tqdm'bash train_linknet_dist.sh --data-path /path/to/coco2017/ --dataset coco