RuntimeError: Error(s) in loading state_dict for BNInception:size mismatch for

花了半天终于解决这个问题了，
Traceback (most recent call last):File "test_video.py", line 105, in <module>img_feature_dim=args.img_feature_dim, print_spec=False)File "/data2/zcq1/TRN-pytorch/models.py", line 43, in __init__self._prepare_base_model(base_model)File "/data2/zcq1/TRN-pytorch/models.py", line 108, in _prepare_base_modelself.base_model = getattr(model_zoo, base_model)()File "/data2/zcq1/TRN-pytorch/model_zoo/bninception/pytorch_load.py", line 38, in __init__self.load_state_dict(torch.utils.model_zoo.load_url(weight_url, model_dir='/data2/zcq1/TRN-pytorch/model_zoo'))File "/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py", line 847, in load_state_dictself.__class__.__name__, "\n\t".join(error_msgs)))
RuntimeError: Error(s) in loading state_dict for BNInception:size mismatch for conv1_7x7_s2_bn.weight: copying a param with shape torch.Size([1, 64]) from checkpoint, the shape in current model is torch.Size([64]).size mismatch for conv1_7x7_s2_bn.bias: copying a param with shape torch.Size([1, 64]) from checkpoint, the shape in current model is torch.Size([64]).size mismatch for conv1_7x7_s2_bn.running_mean: copying a param with shape torch.Size([1, 64]) from checkpoint, the shape in current model is torch.Size([64]).size mismatch for conv1_7x7_s2_bn.running_var: copying a param with shape torch.Size([1, 64]) from checkpoint, the shape in current model is torch.Size([64]).size mismatch for conv2_3x3_reduce_bn.weight: copying a param with shape torch.Size([1, 64]) from checkpoint, the shape in current model is torch.Size([64]).size mismatch for conv2_3x3_reduce_bn.bias: copying a param with shape torch.Size([1, 64]) from checkpoint, the shape in current model is torch.Size([64]).size mismatch for conv2_3x3_reduce_bn.running_mean: copying a param with shape torch.Size([1, 64]) from checkpoint, the shape in current model is torch.Size([64]).size mismatch for conv2_3x3_reduce_bn.running_var: copying a param with shape torch.Size([1, 64]) from checkpoint, the shape in current model is torch.Size([64]).size mismatch for conv2_3x3_bn.weight: copying a param with shape torch.Size([1, 192]) from checkpoint, the shape in current model is torch.Size([192]).size mismatch for conv2_3x3_bn.bias: copying a param with shape torch.Size([1, 192]) from checkpoint, the shape in current model is torch.Size([192]).size mismatch for conv2_3x3_bn.running_mean: copying a param with shape torch.Size([1, 192]) from checkpoint, the shape in current model is torch.Size([192]).size mismatch for conv2_3x3_bn.running_var: copying a param with shape torch.Size([1, 192]) from checkpoint, the shape in current model is torch.Size([192]).size mismatch for inception_3a_1x1_bn.weight: copying a param with shape torch.Size([1, 64]) from checkpoint, the shape in current model is torch.Size([64]).size mismatch for inception_3a_1x1_bn.bias: copying a param with shape torch.Size([1, 64]) from checkpoint, the shape in current model is torch.Size([64]).size mismatch for inception_3a_1x1_bn.running_mean: copying a param with shape torch.Size([1, 64]) from checkpoint, the shape in current model is torch.Size([64]).size mismatch for inception_3a_1x1_bn.running_var: copying a param with shape torch.Size([1, 64]) from checkpoint, the shape in current model is torch.Size([64]).size mismatch for inception_3a_3x3_reduce_bn.weight: copying a param with shape torch.Size([1, 64]) from checkpoint, the shape in current model is torch.Size([64]).size mismatch for inception_3a_3x3_reduce_bn.bias: copying a param with shape torch.Size([1, 64]) from checkpoint, the shape in current model is torch.Size([64]).size mismatch for inception_3a_3x3_reduce_bn.running_mean: copying a param with shape torch.Size([1, 64]) from checkpoint, the shape in current model is torch.Size([64]).size mismatch for inception_3a_3x3_reduce_bn.running_var: copying a param with shape torch.Size([1, 64]) from checkpoint, the shape in current model is torch.Size([64]).size mismatch for inception_3a_3x3_bn.weight: copying a param with shape torch.Size([1, 64]) from checkpoint, the shape in current model is torch.Size([64]).size mismatch for inception_3a_3x3_bn.bias: copying a param with shape torch.Size([1, 64]) from checkpoint, the shape in current model is torch.Size([64]).size mismatch for inception_3a_3x3_bn.running_mean: copying a param with shape torch.Size([1, 64]) from checkpoint, the shape in current model is torch.Size([64]).size mismatch for inception_3a_3x3_bn.running_var: copying a param with shape torch.Size([1, 64]) from checkpoint, the shape in current model is torch.Size([64]).size mismatch for inception_3a_double_3x3_reduce_bn.weight: copying a param with shape torch.Size([1, 64]) from checkpoint, the shape in current model is torch.Size([64]).size mismatch for inception_3a_double_3x3_reduce_bn.bias: copying a param with shape torch.Size([1, 64]) from checkpoint, the shape in current model is torch.Size([64]).解决前的代码是这样的：
self.load_state_dict(torch.utils.model_zoo.load_url(weight_url, model_dir='./TRN-pytorch-master/model_zoo'))解决后：
model_BNInception = torch.utils.model_zoo.load_url(weight_url, model_dir='./TRN-pytorch-master/model_zoo')for name, weights in model_BNInception.items():# print(name, weights.size())  可以查看模型中的模型名字和权重维度if len(weights.size()) == 2: #判断需要修改维度的条件model_BNInception[name] = weights.squeeze(0)  #去掉维度0，把(1,128)转为(128)self.load_state_dict(model_BNInception)终于解决了，希望别人不要像我一样再浪费时间慢慢解决这个问题，特此共享一下解决方法

RuntimeError: Error(s) in loading state_dict for BNInception:size mismatch for相关推荐

Error(s) in loading state_dict for ResNet 问题解决
当使用如下命令加载模型的时候,会报错,没有一些 keys: model.load_state_dict(model_zoo.load_url(model_urls['resnet101'])) Run ...
Error(s) in loading state_dict for ModelMain
原代码: net = ModelMain(config, is_training=is_training) net.train(is_training) net = nn.DataParallel(n ...
Error(s) in loading state_dict
这个错误是因为model.load中的model的问题. 你下载到了别人的模型参数文件,但是这个model你必须先按照别人的代码中那个model构造,而不能是你的model. 也就是说,单单下载别人的 ...
测试模型是出现：RuntimeErrorError(s) in loading state_dict for MIMO-UNet
测试模型是出现:RuntimeError:Error(s) in loading state_dict for MIMO-UNet 在测试已经训练好的模型时,一直出现RuntimeError的错误,结 ...
RuntimeError: Error occured during execution of the processing block! See the log for more info
Intel Realsense报错:RuntimeError: Error occured during execution of the processing block! See the log ...
【已解决】Error occurred during loading data. Trying to use cache server_Python系列学习笔记
报错: Error occurred during loading data. Trying to use cache server Error occurred during loading dat ...
ERROR 3948 (42000): Loading local data is disabled问题解决
服务器版本: Server version: 8.0.20-0ubuntu0.19.10.1 (Ubuntu) 完整报错如下: ERROR 3948 (42000): Loading local da ...
mongodb报错 An error occurred while loading navigation: topology was destroyed
情况描述,关了电脑,第二天查询数据,报错An error occurred while loading navigation: topology was destroyed 我的数据库连接代码如下: ...
ubuntu开机出现错误“Error found when loading /root/.profile”解决
在刚修改完root权限自动登录后,发现开机出现以下提示: Error found when loading /root/.profile stdin:is not a tty ============ ...
最近项目开发再一次遇到了启动idea报错：Plugin Error Problems found loading plugins: Plugin “GlassFish Integration“ was
最近项目开发再一次遇到了启动idea报错:Plugin Error Problems found loading plugins: Plugin "GlassFish Integration ...

RuntimeError: Error(s) in loading state_dict for BNInception:size mismatch for

RuntimeError: Error(s) in loading state_dict for BNInception:size mismatch for相关推荐

最新文章

热门文章