search

jfzhang95 / pytorch-video-recognition

PyTorch implemented C3D, R3D, R2Plus1D models for video activity recognition.
MIT License
1.16k stars 250 forks source link

Questions about train_params？ #61

Closed Taylor-X76 closed 3 years ago

Taylor-X76 commented 3 years ago 
    if modelName == 'C3D':
        model = C3D_model.C3D(num_classes=num_classes, pretrained=True)  
        train_params = [{'params': C3D_model.get_1x_lr_params(model), 'lr': lr},
                        {'params': C3D_model.get_10x_lr_params(model), 'lr': lr * 10}]

    optimizer = optim.SGD(train_params, lr=lr, momentum=0.9, weight_decay=5e-4)
    scheduler = optim.lr_scheduler.StepLR(optimizer, step_size=10,
                                          gamma=0.1)

What's the meaning of train_params? Why is there lr * 10?