QuantizableMobileNetV3 Can not load pretrained model #4959
Description
🐛 Describe the bug
import torchvision
quantized = torchvision.models.quantization.mobilenet_v3_large(pretrained=True)It will occur
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/opt/conda/lib/python3.8/site-packages/torchvision/models/quantization/mobilenetv3.py", line 180, in mobilenet_v3_large
return _mobilenet_v3_model(arch, inverted_residual_setting, last_channel, pretrained, progress, quantize, **kwargs)
File "/opt/conda/lib/python3.8/site-packages/torchvision/models/quantization/mobilenetv3.py", line 154, in _mobilenet_v3_model
_load_weights(arch, model, model_urls.get(arch, None), progress)
File "/opt/conda/lib/python3.8/site-packages/torchvision/models/quantization/mobilenetv3.py", line 124, in _load_weights
model.load_state_dict(state_dict)
File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1482, in load_state_dict
raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for QuantizableMobileNetV3:
Unexpected key(s) in state_dict: "features.4.block.2.scale_activation.activation_post_process.scale", "features.4.block.2.scale_activation.activation_post_process.zero_point", "features.4.block.2.scale_activation.activation_post_process.fake_quant_enabled", "features.4.block.2.scale_activation.activation_post_process.observer_enabled", "features.5.block.2.scale_activation.activation_post_process.scale", "features.5.block.2.scale_activation.activation_post_process.zero_point", "features.5.block.2.scale_activation.activation_post_process.fake_quant_enabled", "features.5.block.2.scale_activation.activation_post_process.observer_enabled", "features.6.block.2.scale_activation.activation_post_process.scale", "features.6.block.2.scale_activation.activation_post_process.zero_point", "features.6.block.2.scale_activation.activation_post_process.fake_quant_enabled", "features.6.block.2.scale_activation.activation_post_process.observer_enabled", "features.11.block.2.scale_activation.activation_post_process.scale", "features.11.block.2.scale_activation.activation_post_process.zero_point", "features.11.block.2.scale_activation.activation_post_process.fake_quant_enabled", "features.11.block.2.scale_activation.activation_post_process.observer_enabled", "features.12.block.2.scale_activation.activation_post_process.scale", "features.12.block.2.scale_activation.activation_post_process.zero_point", "features.12.block.2.scale_activation.activation_post_process.fake_quant_enabled", "features.12.block.2.scale_activation.activation_post_process.observer_enabled", "features.13.block.2.scale_activation.activation_post_process.scale", "features.13.block.2.scale_activation.activation_post_process.zero_point", "features.13.block.2.scale_activation.activation_post_process.fake_quant_enabled", "features.13.block.2.scale_activation.activation_post_process.observer_enabled", "features.14.block.2.scale_activation.activation_post_process.scale", "features.14.block.2.scale_activation.activation_post_process.zero_point", "features.14.block.2.scale_activation.activation_post_process.fake_quant_enabled", "features.14.block.2.scale_activation.activation_post_process.observer_enabled", "features.15.block.2.scale_activation.activation_post_process.scale", "features.15.block.2.scale_activation.activation_post_process.zero_point", "features.15.block.2.scale_activation.activation_post_process.fake_quant_enabled", "features.15.block.2.scale_activation.activation_post_process.observer_enabled".
Versions
PyTorch version: 1.10.0+cu113
Is debug build: False
CUDA used to build PyTorch: 11.3
ROCM used to build PyTorch: N/A
OS: Ubuntu 20.04.1 LTS (x86_64)
GCC version: (Ubuntu 9.3.0-17ubuntu1~20.04) 9.3.0
Clang version: Could not collect
CMake version: version 3.19.4
Libc version: glibc-2.31
Python version: 3.8.5 (default, Sep 4 2020, 07:30:14) [GCC 7.3.0] (64-bit runtime)
Python platform: Linux-5.4.0-90-generic-x86_64-with-glibc2.10
Is CUDA available: True
CUDA runtime version: 11.2.67
GPU models and configuration: GPU 0: NVIDIA GeForce RTX 3090
Nvidia driver version: 470.82.00
cuDNN version: Probably one of the following:
/usr/lib/x86_64-linux-gnu/libcudnn.so.8.1.0
/usr/lib/x86_64-linux-gnu/libcudnn_adv_infer.so.8.1.0
/usr/lib/x86_64-linux-gnu/libcudnn_adv_train.so.8.1.0
/usr/lib/x86_64-linux-gnu/libcudnn_cnn_infer.so.8.1.0
/usr/lib/x86_64-linux-gnu/libcudnn_cnn_train.so.8.1.0
/usr/lib/x86_64-linux-gnu/libcudnn_ops_infer.so.8.1.0
/usr/lib/x86_64-linux-gnu/libcudnn_ops_train.so.8.1.0
HIP runtime version: N/A
MIOpen runtime version: N/A
Versions of relevant libraries:
[pip3] numpy==1.19.2
[pip3] pytorch-transformers==1.1.0
[pip3] torch==1.10.0+cu113
[pip3] torchaudio==0.10.0+cu113
[pip3] torchtext==0.11.0
[pip3] torchvision==0.11.1+cu113
[conda] magma-cuda110 2.5.2 5 local
[conda] mkl 2019.4 243
[conda] mkl-include 2019.4 243
[conda] nomkl 3.0 0
[conda] numpy 1.19.2 py38h6163131_0
[conda] numpy-base 1.19.2 py38h75fe3a5_0
[conda] pytorch-transformers 1.1.0 pypi_0 pypi
[conda] torch 1.10.0+cu113 pypi_0 pypi
[conda] torchaudio 0.10.0+cu113 pypi_0 pypi
[conda] torchtext 0.11.0 pypi_0 pypi
[conda] torchvision 0.11.1+cu113 pypi_0 pypi