training with the pretrained model 'resnext-101-kinetics-hmdb51_split1.pth', cannot success

[cs-heibao]

` if opt.resume_path: print('loading checkpoint {}'.format(opt.resume_path)) checkpoint = torch.load(opt.resume_path) assert opt.arch == checkpoint['arch']

    opt.begin_epoch = checkpoint['epoch']
    model.load_state_dict(checkpoint['state_dict'],strict=False)
    if not opt.no_train:
        optimizer.load_state_dict(checkpoint['optimizer'])

` the last line 'optimizer.load_state_dict(checkpoint['optimizer'])' cannot success, and the error is ValueError: loaded state dict has a different number of parameter groups

hope to give some instructions, thanks!

[cs-heibao]

the problem is solved, thanks

[sudonto]

hi @cs-heibao , may i know how you solve your issue? thanks.

UPDATE: i solve this by looking at this answer if anyone experience the same.