Train and evaluate all of present Object Detection and Segmentation models.
Although previous projects implement multiple models(Detectron2, MMDetection and so on), these are missingsome of vision models. Our goal is to implement all of models by only using our project.
- PyTorch : >=1.5
- TensorFlow : >=1.15.0
- CUDA : >=10.2
git clone https://github.com/major196512/vistem
python -m pip install -e vistem
cd vistem
ln -s $PRETRAINED pretrained_weights
ln -s $DATA data$PRETRAINED : the directory of pretrained backbone network weights(download pretrained models from here)
$DATA : the directory of datasets(See here for more information).
We train our models with 8-gpu and 16 images per batch.
| Meta Architecture |
Backbone Network |
BBox AP |
BBox AP50 |
BBox AP75 |
Config File |
|---|---|---|---|---|---|
| RetinaNet | ResNet-50 with FPN |
55.533 | 81.730 | 60.504 | retinanet_R50_FPN |
| RetinaNet | ResNet-50 with NAS-FPN |
In Progress | retinanet_R50_NASFPN | ||
| Faster RCNN | ResNet-50 with FPN |
54.282 | 81.827 | 60.048 | faster_R50_FPN |
| Faster RCNN | ResNet-50 with NAS-FPN |
In Progress | faster_R50_NASFPN | ||
| CornerNet | ResNet-50 with FPN |
In Progress | |||
| RepPoints | ResNet-50 with FPN |
In Progress |
When training using Gradient Accumulation, you must assign a cfg.SOLVER.ACUUMULATE and cfg.SOLVER.IMG_PER_BATCH in config file.
In this table below, we run our models with 4 gradient accumulation and 4 images per batch with 2-gpu.
| Meta Architecture |
Backbone Network |
BBox AP |
BBox AP50 |
BBox AP75 |
|---|---|---|---|---|
| RetinaNet | ResNet-50 with FPN |
51.011 | 79.542 | 54.105 |
| RetinaNet | ResNet-50 with NAS-FPN |
In Progress | ||
| Faster RCNN | ResNet-50 with FPN |
49.928 | 80.683 | 53.101 |
| Faster RCNN | ResNet-50 with NAS-FPN |
In Progress | ||
| CornerNet | ResNet-50 with FPN |
In Progress | ||
| RepPoints | ResNet-50 with FPN |
In Progress |
In training MS-COCO datasets, We only evaluate with 8-gpu settings.
| Meta Architecture |
Backbone Network |
BBox AP |
Config File |
|---|---|---|---|
| RetinaNet | ResNet-50 with FPN |
36.524 | retinanet_R50_FPN |
| RetinaNet | ResNet-50 with FPN |
In Progress | retinanet_R50_NASFPN |
| Faster RCNN | ResNet-50 with FPN |
38.021 | faster_R50_FPN |
| Faster RCNN | ResNet-50 with NAS-FPN |
In Progress | faster_R50_NASFPN |
| CornerNet | ResNet-50 with FPN |
In Progress | |
| RepPoints | ResNet-50 with FPN |
In Progress |
When training in a single machine, you should only specify --config-file and --num-gpu in argument.
You can select the training model and datasets by using or modifying a config file. For more information about factors in config, see here.
python tools/train.py --config-file ./configs/RetinaNet/VOC-Detection/R50_FPN_1x_8gpu.yaml --num-gpu 8If you want to resume training, just set --resume in argument.
python tools/train.py --config-file ./configs/RetinaNet/VOC-Detection/R50_FPN_1x_8gpu.yaml --num-gpu 8 --resumeFor collective communication in pytorch, it needs to execute process in main machine. They automatically set main machine IP address and unused port number for TCP communication.
For main process, you must set machine-rank to zero and num-machine to the number of machines.
python tools/train.py --config-file ./configs/train.yaml --num-gpu 4 --num-machine 2 --machine-rank 0In other machines, you clarify machine-rank and must set dist-ip and dist-port arguments which is the same with main machine values.
python tools/train.py --config-file ./configs/train.yaml --num-gpu 4 --num-machine 2 --machine-rank 1 --dist-ip xxx.xxx.xxx.xxx --dist-port xxxxpython tools/test.py --config-file ./configs/test.yaml --eval-only