KeyError: ‘XXX.model.1.num_batches_tracked‘

Loading trained model weights...
Traceback (most recent call last):
  File "F:/weakalign-master/demo.py", line 71, in <module>
    model.FeatureExtraction.state_dict()[name].copy_(checkpoint['state_dict']['FeatureExtraction.' + name])    
KeyError: 'FeatureExtraction.model.1.num_batches_tracked'

源代码：

print('Loading trained model weights...')
if args.model != '':
    checkpoint = torch.load(args.model, map_location=lambda storage, loc: storage)
    checkpoint['state_dict'] = OrderedDict([(k.replace('vgg', 'model'), v) for k, v in checkpoint['state_dict'].items()])
        
    for name, param in model.FeatureExtraction.state_dict().items():
        model.FeatureExtraction.state_dict()[name].copy_(checkpoint['state_dict']['FeatureExtraction.' + name])    
    for name, param in model.FeatureRegression.state_dict().items():
        model.FeatureRegression.state_dict()[name].copy_(checkpoint['state_dict']['FeatureRegression.' + name])
    for name, param in model.FeatureRegression2.state_dict().items():
        model.FeatureRegression2.state_dict()[name].copy_(checkpoint['state_dict']['FeatureRegression2.' + name])
        
else:
    checkpoint_aff = torch.load(args.model_aff, map_location=lambda storage, loc: storage)
    checkpoint_aff['state_dict'] = OrderedDict([(k.replace('vgg', 'model'), v) for k, v in checkpoint_aff['state_dict'].items()])
    for name, param in model.FeatureExtraction.state_dict().items():
        model.FeatureExtraction.state_dict()[name].copy_(checkpoint_aff['state_dict']['FeatureExtraction.' + name])    
    for name, param in model.FeatureRegression.state_dict().items():
        model.FeatureRegression.state_dict()[name].copy_(checkpoint_aff['state_dict']['FeatureRegression.' + name])

这行代码model.FeatureExtraction.state_dict()[name].copy_(checkpoint['state_dict']['FeatureExtraction.' + name])    报错了，先检查一下各个参数的数据格式对不对，然后再看看模型问题

您好，我是有问必答小助手，您的问题已经有小伙伴解答了，您看下是否解决，可以追评进行沟通哦~

如果有您比较满意的答案 / 帮您提供解决思路的答案，可以点击【采纳】按钮，给回答的小伙伴一些鼓励哦～～

ps:问答VIP仅需29元，即可享受5次/月 有问必答服务，了解详情>>>https://vip.csdn.net/askvip?utm_source=1146287632