For modify the original mask rcnn model. Please connect the models in the model/modified_mask_rcnn.py
python=3.7.7
pytorch=1.6.0=py3.7_cuda10.1.243_cudnn7.6.3_0
torchvision=0.7.0=py37_cu101
numpy=1.19.1=py37hbc911f0_0
conda env create -f environment.yml -n rcnnconda activate rcnn./download_pedestrian.sh
python test_pedestrian.py
When you want to train on pascal voc. you don't need to run the .sh file because it is a built-in function in voc_utils.
python train_voc.py
- cannot run .sh file
chmod 777 YOUR_SH_FILE_NAME.sh
python -m torch.distributed.launch --nproc_per_node=4 --use_env train_coco.py
python -m torch.distributed.launch --nproc_per_node= --use_env train_coco\
--dataset coco --model maskrcnn_resnet50_fpn --epochs 26\
--lr-steps 16 22 --aspect-ratio-group-factor 3
python -m torch.distributed.launch --nproc_per_node=4 --use_env train_coco\
--dataset coco --model maskrcnn_resnet50_fpn --epochs 26\
--lr-steps 16 22 --aspect-ratio-group-factor 3kill $(ps aux | grep train_coco.py | grep -v grep | awk '{print $2}') 
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent