My TVM version - 0.9.dev334+g3c8de42a0
x=torch.randn([1,256,35,35])
upsample_layer = nn.ModuleList([nn.ConvTranspose2d(256, 256, 3, stride=2, padding=1)])
x = upsample_layer(x, output_size=torch.Size([1, 256, 69, 69]))
Line:
mod, params = relay.frontend.from_pytorch(script_module, shape_list)
Error:
NotImplementedError: The following operators are not implemented: ['aten::uniform_']
Is there any PR awaiting to support this operator?