Closed itruonghai closed 10 months ago
Hi, thanks for raising this up. Now this issue has been fixed with the 1.0.0.post2
release
Could you please check and rerun it again? I still find an error. It seems like the attention weight parameter does not necessary in this case. However, when I removed attention_weights parameter in the forward, it raise an error assert (input_spatial_shapes[:, 0] * input_spatial_shapes[:, 1]).sum() == Len_in RuntimeError: CUDA error: an illegal memory access was encountered
+1
same problem @YuwenXiong
Dear Author,
In the module file, DCNv4 function is called with 6 parameters. However, in the forward function, it applied to 8 parameters. Could you correct it?