search

okankop / Efficient-3DCNNs

PyTorch Implementation of "Resource Efficient 3D Convolutional Neural Networks", codes and pretrained models.
MIT License
777 stars 151 forks source link

onnx export problem #15

Open Nioolek opened 4 years ago

Nioolek commented 4 years ago

I tried to convert the 3DCNN model to onnx,but the inference results by onnx and pytorch are different.I tried the backbone of resnet18 and mobilenet.Did anybody meet the same problem?

Environment: CUDA 10.0 CUDNN 7 TENSORRT 7 PYTORCH 1.2.0

CODE:

model, parameters = generate_model(opt)
checkpoint = torch.load('my_mobilenet_1.0x_RGB_10_checkpoint.pth')

model.load_state_dict(checkpoint['state_dict'])
print('load checkpoint')
if isinstance(model, torch.nn.DataParallel):
    model = model.module

x = torch.ones((1, 3, 10, 128, 128)).cuda()

y = model(x)
print(y)

torch.onnx.export(model, x, '3dcnn.onnx', verbose=True)
okankop commented 4 years ago

I never tried to cenvert these models to onnx, but in principle it should be possible. When I have time, I would try and let you know.

poincarelee commented 2 years ago

@okankop After two years, still didn't try on exporting to onnx ? I saw several questions about low accuracy of pretrained models, didn't do any update?