duanyuqi987
commented
4 years ago torch RuntimeError: Error(s) in loading state_dict for CRNN:???
加载训练的模型报如下错误。
model.load_state_dict(torch.load(model_path)) Traceback (most recent call last): File "
", line 1, in File "/usr/local/lib/python2.7/dist-packages/torch/nn/modules/module.py", line 777, in load_state_dict self.class.name, "\n\t".join(error_msgs))) RuntimeError: Error(s) in loading state_dict for CRNN: Missing key(s) in state_dict: "cnn.conv0.bias", "cnn.conv0.weight", "cnn.conv1.bias", "cnn.conv1.weight", "cnn.conv2.bias", "cnn.conv2.weight", "cnn.batchnorm2.running_var", "cnn.batchnorm2.bias", "cnn.batchnorm2.weight", "cnn.batchnorm2.running_mean", "cnn.conv3.bias", "cnn.conv3.weight", "cnn.conv4.bias", "cnn.conv4.weight", "cnn.batchnorm4.running_var", "cnn.batchnorm4.bias", "cnn.batchnorm4.weight", "cnn.batchnorm4.running_mean", "cnn.conv5.bias", "cnn.conv5.weight", "cnn.conv6.bias", "cnn.conv6.weight", "cnn.batchnorm6.running_var", "cnn.batchnorm6.bias", "cnn.batchnorm6.weight", "cnn.batchnorm6.running_mean", "rnn.0.rnn.bias_ih_l0_reverse", "rnn.0.rnn.weight_hh_l0_reverse", "rnn.0.rnn.bias_ih_l0", "rnn.0.rnn.bias_hh_l0", "rnn.0.rnn.weight_ih_l0_reverse", "rnn.0.rnn.weight_ih_l0", "rnn.0.rnn.bias_hh_l0_reverse", "rnn.0.rnn.weight_hh_l0", "rnn.0.embedding.bias", "rnn.0.embedding.weight", "rnn.1.rnn.bias_ih_l0_reverse", "rnn.1.rnn.weight_hh_l0_reverse", "rnn.1.rnn.bias_ih_l0", "rnn.1.rnn.bias_hh_l0", "rnn.1.rnn.weight_ih_l0_reverse", "rnn.1.rnn.weight_ih_l0", "rnn.1.rnn.bias_hh_l0_reverse", "rnn.1.rnn.weight_hh_l0", "rnn.1.embedding.bias", "rnn.1.embedding.weight". Unexpected key(s) in state_dict: "module.cnn.conv0.weight", "module.cnn.conv0.bias", "module.cnn.conv1.weight", "module.cnn.conv1.bias", "module.cnn.conv2.weight", "module.cnn.conv2.bias", "module.cnn.batchnorm2.weight", "module.cnn.batchnorm2.bias", "module.cnn.batchnorm2.running_mean", "module.cnn.batchnorm2.running_var", "module.cnn.batchnorm2.num_batches_tracked", "module.cnn.conv3.weight", "module.cnn.conv3.bias", "module.cnn.conv4.weight", "module.cnn.conv4.bias", "module.cnn.batchnorm4.weight", "module.cnn.batchnorm4.bias", "module.cnn.batchnorm4.running_mean", "module.cnn.batchnorm4.running_var", "module.cnn.batchnorm4.num_batches_tracked", "module.cnn.conv5.weight", "module.cnn.conv5.bias", "module.cnn.conv6.weight", "module.cnn.conv6.bias", "module.cnn.batchnorm6.weight", "module.cnn.batchnorm6.bias", "module.cnn.batchnorm6.running_mean", "module.cnn.batchnorm6.running_var", "module.cnn.batchnorm6.num_batches_tracked", "module.rnn.0.rnn.weight_ih_l0", "module.rnn.0.rnn.weight_hh_l0", "module.rnn.0.rnn.bias_ih_l0", "module.rnn.0.rnn.bias_hh_l0", "module.rnn.0.rnn.weight_ih_l0_reverse", "module.rnn.0.rnn.weight_hh_l0_reverse", "module.rnn.0.rnn.bias_ih_l0_reverse", "module.rnn.0.rnn.bias_hh_l0_reverse", "module.rnn.0.embedding.weight", "module.rnn.0.embedding.bias", "module.rnn.1.rnn.weight_ih_l0", "module.rnn.1.rnn.weight_hh_l0", "module.rnn.1.rnn.bias_ih_l0", "module.rnn.1.rnn.bias_hh_l0", "module.rnn.1.rnn.weight_ih_l0_reverse", "module.rnn.1.rnn.weight_hh_l0_reverse", "module.rnn.1.rnn.bias_ih_l0_reverse", "module.rnn.1.rnn.bias_hh_l0_reverse", "module.rnn.1.embedding.weight", "module.rnn.1.embedding.bias".
什么鬼，模型字段名称怎么多了个module的前缀，查看，修改名字即可。
dir(torch.load(model_path)) ['_OrderedDictmap', '_OrderedDict__marker', '_OrderedDictroot', '_OrderedDictupdate', 'class', 'cmp', 'contains', 'delattr', 'delitem', 'dict', 'doc', 'eq', 'format', 'ge', 'getattribute', 'getitem', 'gt', 'hash', 'init', 'iter', 'le', 'len', 'lt', 'module', 'ne', 'new', 'reduce', 'reduce_ex', 'repr', 'reversed', 'setattr', 'setitem', 'sizeof', 'str', 'subclasshook', 'weakref__', 'clear', 'copy', 'fromkeys', 'get', 'has_key', 'items', 'iteritems', 'iterkeys', 'itervalues', 'keys', 'pop', 'popitem', 'setdefault', 'update', 'values', 'viewitems', 'viewkeys', 'viewvalues']
model.load_state_dict({k.replace('module.',''):v for k,v in torch.load(model_path).items()}) IncompatibleKeys(missing_keys=[], unexpected_keys=[])
参考文献：
Pytorch：Unexpected key(s) in state_dict:
１．torch.load invalid load key, '\x00'？？？ MaskDetection_yolo3_pytorch项目中导入参数的时候出现的错误
答： torch加载yolov3.weights，报错：
torch.load invalid load key, '\x00'
`cfg='cfg/yolov3.cfg' model = Darknet(cfg, img_size)
加载权重，保存权重，转换权重 `def load_darknet_weights(self, weights, cutoff=-1):
Parses and loads the weights stored in 'weights'
def save_weights(self, path='model.weights', cutoff=-1):
Converts a PyTorch model to Darket format (.pt to .weights)
def convert(cfg='cfg/yolov3-spp.cfg', weights='weights/yolov3-spp.weights'):
Converts between PyTorch and Darknet format per extension (i.e. .weights convert to .pt and vice versa)