Keewon Shin

I did inference with my own dataset, and I was wondering if anyone else had the same problem with inference results as me. I'll try to figure out the problem...

As mentioned above, I trained a 3d_fullres nnU-Net using my own dataset and expected to get the same results if I performed inferences on the same weights.  The picture...

Try this. ` nestnet_output_all = keras.layers.Average()([nestnet_output_1,nestnet_output_2,nestnet_output_3,nestnet_output_4]) if deep_supervision: model = Model(inputs=[img_input], outputs=[nestnet_output_all]) else: model = Model(inputs=img_input, outputs=[nestnet_output_4])`

ACDC dataset has only 1 input_channel. Thus, in "dataloader.py", I add this line after line 383 to append image in 3 channels. img = Image.open(img_path) img = img.convert('RGB') #