conv-neural-network - 在训练 resnet18 模型时，我发现卷积的权重并没有被 tensorboard 改变。如何处理这个问题？

Question

resnet18的权重如下：

resnet18的卷积权重 resnet18的
卷积权重

具体型号如下：

DataParallel(
  (module): CsResnet(
    (base_model): ResNet(
      (conv1): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)
      (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace=True)
      (maxpool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
      (layer1): Sequential(
        (0): BasicBlock(
          (conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): ReLU(inplace=True)
          (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
        (1): BasicBlock(
          (conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): ReLU(inplace=True)
          (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
      (layer2): Sequential(
        (0): BasicBlock(
          (conv1): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
          (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): ReLU(inplace=True)
          (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (downsample): Sequential(
            (0): Conv2d(64, 128, kernel_size=(1, 1), stride=(2, 2), bias=False)
            (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          )
        )
        (1): BasicBlock(
          (conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): ReLU(inplace=True)
          (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
      (layer3): Sequential(
        (0): BasicBlock(
          (conv1): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
          (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): ReLU(inplace=True)
          (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (downsample): Sequential(
            (0): Conv2d(128, 256, kernel_size=(1, 1), stride=(2, 2), bias=False)
            (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          )
        )
        (1): BasicBlock(
          (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): ReLU(inplace=True)
          (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
      (layer4): Sequential(
        (0): BasicBlock(
          (conv1): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
          (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): ReLU(inplace=True)
          (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (downsample): Sequential(
            (0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)
            (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          )
        )
        (1): BasicBlock(
          (conv1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (relu): ReLU(inplace=True)
          (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        )
      )
      (avgpool): AdaptiveAvgPool2d(output_size=(1, 1))
      (fc): Linear(in_features=512, out_features=101, bias=True)
    )
    (consensus): ConsensusModule()
    (single_channel_fc): Linear(in_features=1003, out_features=50176, bias=True)
    (recovery_normal): BatchNorm1d(50176, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    (single_channel_activate_function): Tanh()
  )
)

我的主要培训演示如下：

model = getattr(cs_model, "resnet18")(num_classes=args.num_classes, num_segments=args.num_segments,
                                            modality="RGB",
                                            new_length=args.new_length, consensus_type=args.consensus_type,
                                            dropout=args.dropout, crop_num=args.crop_num, partial_bn=args.partial_bn,
                                            recovery_width=args.recovery_width, recovery_height=args.recovery_height,
                                            y_cs=y_cs)
    model = torch.nn.DataParallel(model).cuda()

optimizer = torch.optim.SGD(model.parameters(), args.lr, momentum=args.momentum, weight_decay=args.weight_decay)

    for epoch in range(args.start_epoch, args.epochs):
        adjust_learning_rate(args, optimizer, epoch, args.lr_steps)

        # train for one epoch
        train(args, train_loader, model, teacher_model, criterion, mse_criterion,optimizer, epoch, tb_writer)

        # evaluate on validation set
        if (epoch + 1) % args.eval_freq == 0 or epoch == args.epochs - 1:
            prec1 = validate(args, val_loader, model, teacher_model, criterion, mse_criterion, epoch, tb_writer)

            # remember best prec@1 and save checkpoint
            is_best = prec1 > best_prec1
            best_prec1 = max(prec1, best_prec1)
            save_checkpoint(args, {
                'epoch': epoch + 1,
                'arch': args.arch,
                'state_dict': model.state_dict(),
                'best_prec1': best_prec1,
            }, is_best)


def adjust_learning_rate(args, optimizer, epoch, lr_steps):
    """Sets the learning rate to the initial LR decayed by 10 every 30 epochs"""
    if args.student_modality != "cs":
        decay = 0.1 ** (sum(epoch >= np.array(lr_steps)))
        lr = args.lr * decay
        decay = args.weight_decay
        for param_group in optimizer.param_groups:
            param_group['lr'] = lr * param_group['lr_mult']
            param_group['weight_decay'] = decay * param_group['decay_mult']
    elif epoch in lr_steps:
        lr = args.lr * 0.1
        for param_group in optimizer.param_groups:
            param_group['lr'] = lr  # * param_group['lr_mult']
            param_group['weight_decay'] = args.weight_decay

我训练这个网络对 ucf101 进行分类。但是，我发现 resnet-18 的卷积在训练过程中并没有改变。有谁知道如何解决这个问题？非常感谢。

标签： conv-neural-network