Error for loading vgg16_reducedfc for exporting to onnx model about pytorch-ssd

[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.)