Run training and evaluation :
python train_eval.py --cfg path/to/your/yaml
and replace path/to/your/yaml
by path to your configuration file, e.g. :
python train_eval.py --cfg experiments/vgg16_pca_voc.yaml
Default configuration files are in yaml
format and are stored in experiments/
.
Note
You are welcomed to try your own configurations. If you find a better yaml configuration, please let us know by raising an issue or a PR and we will update the benchmark!
ThinkMatch provides pretrained models. The model weights are available via google drive.
- To use the pretrained models, firstly download the weight files, then add the following line to your yaml file:
PRETRAINED_PATH: path/to/your/pretrained/weights
- The naming of pretrained weights follows:
"prefix"_"CNN backbone"_"model name"_"dataset name".pt
- Example:
pretrained_params_vgg16_bbgm_voc.pt "prefix": pretrained_params "CNN backbone": vgg16 "model name": bbgm "dataset name": voc