A litte bug in tools/plain_train_net.py .

JDAI-CV / fast-reid

SOTA Re-identification Methods and Toolbox

Apache License 2.0

3.42k stars 837 forks source link

A litte bug in tools/plain_train_net.py . #657

Closed LorenzoSun-V closed 2 years ago

LorenzoSun-V commented 2 years ago

optimizer = build_optimizer(cfg, model) should be overwrite by optimizer, param_wrapper = build_optimizer(cfg, model)

And you use function "auto_scale_hyperparams" in a trainer but in a plain training way. It may cause bugs when model does inferring. In tools/plain_train_net.py, the training model should be initialized as:

data_loader = build_reid_train_loader(cfg)
cfg = auto_scale_hyperparams(cfg, data_loader.dataset.num_classes)
model = build_model(cfg)

github-actions[bot] commented 2 years ago

This issue is stale because it has been open for 30 days with no activity.

github-actions[bot] commented 2 years ago

This issue was closed because it has been inactive for 14 days since being marked as stale.