This thread has been locked.

If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.

TDA4VM: TDA4VM: Not able to infer high resolution images on target

Part Number: TDA4VM

Tool/software:

Dear Team,

I am trying to infer image of size (512 x 1024) on the target, but it is giving me below error.

Although, the same network I am able to infer at (320 x 512) resolution on target.
Also, when I am removing below layers, then I am able to infer on target at (512 x 1024) resolution:

'''

1. self.avg_layer = nn.AvgPool2d(kernel_size=3, stride=1, padding=1)
2.
def channel_shuffle(x, groups):

         b, c, h, w = x.shape
         x = x.reshape(b, groups, -1, h, w)
         x = x.permute(0, 2, 1, 3, 4)
         x   = x.reshape(b, -1, h, w)
    return x
'''

Is there something which I can change during importing the ONNX? 

Thanks and Regards,

Adarsh Kumar