gait-recognition.git/test, branch data_parallel_py3.8

Code refactoring

2021-03-12T05:56:17+00:00

1. Separate FCs and triplet losses for HPM and PartNet
2. Remove FC-equivalent 1x1 conv layers in HPM
3. Support adjustable learning rate schedulers

Enable optimizer fine tuning

2021-01-14T15:43:29+00:00

Update config file and convert int to str when joining

2021-01-13T03:15:04+00:00

Add multiple checkpoints for different model and set default config value

2021-01-13T02:59:59+00:00

Some changes in hyperparameter config

2021-01-12T06:19:30+00:00

1. Separate hyperparameter configs in model, optimizer and scheduler
2. Add more tunable hyperparameters in optimizer and scheduler

Make predict function transform samples different conditions in a single shot

2021-01-10T11:59:37+00:00

Add typical training script and some bug fixes

2021-01-07T10:37:43+00:00

1. Resolve deprecated scheduler stepping issue
2. Make losses in the same scale(replace mean with sum in separate triplet loss, enlarge pose similarity loss 10x)
3. Add ReLU when compute distance in triplet loss
4. Remove classes except Model from `models` package init

Add CUDA support

2021-01-06T14:19:27+00:00

Add TensorBoard support

2021-01-06T13:26:56+00:00

Implement Batch All Triplet Loss

2021-01-05T12:20:06+00:00