<pre> %105 = add(%104, 1f); %106 = reshape(%105, newshape=[8, 1, 512, 1, 1]); %107 = multiply(%3, %106); %108 = full(1, shape=[], dtype="float32"); %109 = power(%107, 2f); %110 = sum(%109); %111 = add(%110, 1e-08f); %112 = power(%111, 0.5f); %113 = divide(%108, %112); %114 = multiply(%113, 1f); %115 = reshape(%114, newshape=[8, 512, 1, 1, 1]); %116 = multiply(%107, %115); %117 = reshape(%116, newshape=[4096, 512, 3, 3]); %118 = nn.conv2d(%1, %117, padding=[1, 1, 1, 1], channels=4096, kernel_size=[3, 3])<font color="#CC0000"> in particular dimension 1 conflicts 4096 does not match 512; unable to unify: `Tensor[(4096, 4096, 3, 3), float32]` and `Tensor[(4096, 512, 3, 3), float32]`; </font>; reshape(%118, newshape=[8, 512, 4, 4]) }
</pre> --- [Visit Topic](https://discuss.tvm.ai/t/pytorch-onnx-model-nn-conv2-in-particular-dimension-1-conflicts-4096-does-not-match-512/6255/1) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.tvm.ai/email/unsubscribe/c94b68f5899a6aa755f7611c7aba5976dd86a9674c1c17c8f29dbbc89d5dc04c).
