backbone Resnet50_v2的人脸landmark-68点检测模型 剪枝报错

[qiulongquan]

使用 Torch-Pruning对backbone Resnet50_v2的人脸landmark-68点检测模型进行剪枝，可以剪枝，但是使用剪枝后的模型预测会出现报错

剪枝log Network_resnet50( (model): ResNet( (conv1): Conv2d(1, 32, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False) (bn1): BatchNorm2d(32, 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): Bottleneck( (conv1): Conv2d(32, 32, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (conv2): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (conv3): Conv2d(32, 128, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) (downsample): Sequential( (0): Conv2d(32, 128, kernel_size=(1, 1), stride=(1, 1), bias=False) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (1): Bottleneck( (conv1): Conv2d(128, 32, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (conv2): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (conv3): Conv2d(32, 128, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) ) (2): Bottleneck( (conv1): Conv2d(128, 32, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (conv2): Conv2d(32, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (bn2): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (conv3): Conv2d(32, 128, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) ) ) (layer2): Sequential( (0): Bottleneck( (conv1): Conv2d(128, 64, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=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): Bottleneck( (conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=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) (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) ) (2): Bottleneck( (conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=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) (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) ) (3): Bottleneck( (conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=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) (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) ) ) (layer3): Sequential( (0): Bottleneck( (conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=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): Bottleneck( (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=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) (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) ) (2): Bottleneck( (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=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) (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) ) (3): Bottleneck( (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=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) (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) ) (4): Bottleneck( (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=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) (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) ) (5): Bottleneck( (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=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) (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) ) ) (layer4): Sequential( (0): Bottleneck( (conv1): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) (downsample): Sequential( (0): Conv2d(512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False) (1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (1): Bottleneck( (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=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) (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) ) (2): Bottleneck( (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=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) (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False) (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (relu): ReLU(inplace=True) ) ) (avgpool): AdaptiveAvgPool2d(output_size=(1, 1)) (fc): Linear(in_features=1024, out_features=68, bias=True) ) ) Summary: Params: 23.78 M => 5.96 M MACs: 4.04 G => 1.03 G Output.shape: torch.Size([1, 68])

landmark68 关键点预测log WARNING:root:RuntimeOption.set_trt_input_shape will be deprecated in v1.2.0, please use RuntimeOption.trt_option.set_shape() instead. WARNING:root:RuntimeOption.set_trt_cache_file will be deprecated in v1.2.0, please use RuntimeOption.trt_option.serialize_file = /home/seikoist-qiu/total_test_for_emotion/tensorrt_cache/ubuntu_model.trt instead. WARNING:root:RuntimeOption.enable_trt_fp16 will be deprecated in v1.2.0, please use RuntimeOption.trt_option.enable_fp16 = True instead. WARNING:root:RuntimeOption.set_trt_max_batch_size will be deprecated in v1.2.0, please use RuntimeOption.trt_option.max_batch_size = 1 instead. WARNING:root:RuntimeOption.set_trt_max_workspace_size will be deprecated in v1.2.0, please use RuntimeOption.trt_option.max_workspace_size = 1073741824 instead. WARNING:root:RuntimeOption.enable_paddle_trt_collect_shape will be deprecated in v1.2.0, please use RuntimeOption.paddle_infer_option.collect_trt_shape = True instead. [INFO] fastdeploy/runtime/backends/tensorrt/trt_backend.cc(702)::CreateTrtEngineFromOnnx Detect serialized TensorRT Engine file in /home/seikoist-qiu/total_test_for_emotion/tensorrt_cache/ubuntu_model.trt, will load it directly. [INFO] fastdeploy/runtime/backends/tensorrt/trt_backend.cc(108)::LoadTrtCache Build TensorRT Engine from cache file: /home/seikoist-qiu/total_test_for_emotion/tensorrt_cache/ubuntu_model.trt with shape range information as below, [INFO] fastdeploy/runtime/backends/tensorrt/trt_backend.cc(111)::LoadTrtCache Input name: im_shape, shape=[1, 3, 640, 640], min=[1, 3, 640, 640], max=[1, 3, 640, 640]

[INFO] fastdeploy/runtime/runtime.cc(306)::CreateTrtBackend Runtime initialized with Backend::TRT in Device::GPU. ========================device cuda Traceback (most recent call last): File "landmarks_train_vaildation_prune.py", line 593, in validation_single_image(args) File "landmarks_train_vaildation_prune.py", line 458, in validation_single_image best_network.load_state_dict(torch.load(model_path_prune, map_location=device)) File "/home/seikoist-qiu/anaconda3/envs/emotion/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1559, in load_state_dict raise TypeError("Expected state_dict to be dict-like, got {}.".format(type(state_dict))) TypeError: Expected state_dict to be dict-like, got <class 'main.Network_resnet50'>.

请问为什么会出现这样的错误，以及如何解决问题 谢谢