Error for loading vgg16_reducedfc for exporting to onnx model

[YaraAlnaggar]

I'm trying to export the onnx model for vgg16_reducedfc using this command
python3 convert_to_caffe2_models.py vgg16-ssd models/vgg16_reducedfc.pth models/voc-model-labels.txt
but I got the following error

Traceback (most recent call last): File "convert_to_caffe2_models.py", line 51, in <module> net.load(model_path) File "/media/pc/sdb1/pytorch-ssd/vision/ssd/ssd.py", line 135, in load self.load_state_dict(torch.load(model, map_location=lambda storage, loc: storage)) File "/usr/local/lib/python3.5/dist-packages/torch/nn/modules/module.py", line 769, in load_state_dict self.__class__.__name__, "\n\t".join(error_msgs))) RuntimeError: Error(s) in loading state_dict for SSD: Missing key(s) in state_dict: "base_net.0.bias", "base_net.0.weight", "base_net.2.bias", "base_net.2.weight", "base_net.5.bias", "base_net.5.weight", "base_net.7.bias", "base_net.7.weight", "base_net.10.bias", "base_net.10.weight", "base_net.12.bias", "base_net.12.weight", "base_net.14.bias", "base_net.14.weight", "base_net.17.bias", "base_net.17.weight", "base_net.19.bias", "base_net.19.weight", "base_net.21.bias", "base_net.21.weight", "base_net.24.bias", "base_net.24.weight", "base_net.26.bias", "base_net.26.weight", "base_net.28.bias", "base_net.28.weight", "base_net.31.bias", "base_net.31.weight", "base_net.33.bias", "base_net.33.weight", "extras.0.0.bias", "extras.0.0.weight", "extras.0.2.bias", "extras.0.2.weight", "extras.1.0.bias", "extras.1.0.weight", "extras.1.2.bias", "extras.1.2.weight", "extras.2.0.bias", "extras.2.0.weight", "extras.2.2.bias", "extras.2.2.weight", "extras.3.0.bias", "extras.3.0.weight", "extras.3.2.bias", "extras.3.2.weight", "classification_headers.0.bias", "classification_headers.0.weight", "classification_headers.1.bias", "classification_headers.1.weight", "classification_headers.2.bias", "classification_headers.2.weight", "classification_headers.3.bias", "classification_headers.3.weight", "classification_headers.4.bias", "classification_headers.4.weight", "classification_headers.5.bias", "classification_headers.5.weight", "regression_headers.0.bias", "regression_headers.0.weight", "regression_headers.1.bias", "regression_headers.1.weight", "regression_headers.2.bias", "regression_headers.2.weight", "regression_headers.3.bias", "regression_headers.3.weight", "regression_headers.4.bias", "regression_headers.4.weight", "regression_headers.5.bias", "regression_headers.5.weight", "source_layer_add_ons.0.bias", "source_layer_add_ons.0.running_var", "source_layer_add_ons.0.running_mean", "source_layer_add_ons.0.weight". Unexpected key(s) in state_dict: "0.weight", "0.bias", "2.weight", "2.bias", "5.weight", "5.bias", "7.weight", "7.bias", "10.weight", "10.bias", "12.weight", "12.bias", "14.weight", "14.bias", "17.weight", "17.bias", "19.weight", "19.bias", "21.weight", "21.bias", "24.weight", "24.bias", "26.weight", "26.bias", "28.weight", "28.bias", "31.weight", "31.bias", "33.weight", "33.bias".

Is it because vgg16-ssd network definition is different from the reduced one?

[drcdr]

I've had success in exporting two of the ONNX models provided on the project page; here is a summary:

pre-trained model	net-type	Converts?
mobilenet-v1-ssd-mp-0_675.pth	mb1-ssd	Y
mb2-ssd-lite-mp-0_686.pth	mb2-ssd-lite	Y
vgg16-ssd-mp-0_7726.pth	vgg16-ssd	N (MaxPool2d ceil issue)
mobilenet_v1_with_relu_69_5.pth	mb1-ssd	(N: base model)
vgg16_reducedfc	vgg16-ssd	(N: base model)

To get to this point, I've tweaked each create_xxx_ssd function in convert_to_caffe2_models.py to pass device='cpu', and then pass device=device in the call to SSD (otherwise, there is a GPU/CPU storage mismatch ).

The MaxPool ceil issue is described here: onnx/onnx#549
and is due to this line in vgg.py:
layers += [nn.MaxPool2d(kernel_size=2, stride=2, ceil_mode=True)]
I'm not sure if there is a simple way around this (that maintains the accuracy for these pretrained weights) or not.

[qfgaohao]

Hi @YaraAlnaggar , you can only convert ssd models rather than pre-trained imagenet models by using the script in the project.

[qfgaohao]

@drcdr thanks for the nice summary and pointing out the issue related to MaxPool2d.

[ishang3]

@drcdr Do you have resources that show how to parse the onnx output after inference?
I am successfully able to do inference, but not able to understand the output format.

[drcdr]

It's been a long time since I looked at this...but if you can be more specific about what you're looking for, I might be able to help (like what command you are executing, what output specifically you are looking at, etc.)