nk-dev0

Yes, I did see the same outputs during training. All of the sample tests had the same output even though the inputs were different. I have not yet tried the...

I've found that when the train set size is larger than the save_latest_freq or save_display_freq in train.lua, the outputs will all be identical no matter the input image. My original...

Hi, thanks for uploading the new weights. I can successfully train with them to high accuracy, but after I go through the BN computing and BN absorbing steps as outlined...

@Viswa14 @kli-nlpr I basically followed the tutorial, but for changing image resolution just change the first layer in the train prototxt to your desired size, and the label divide factor...

@Viswa14 hmm, no I didn't run into that

@TimoSaemann is training with more than 3 channels easy with ENet? I think I have to change many output params so the shapes match up; any assistance would be appreciated.

What was the fix?

I got a similar output when using 3 classes as well, but I went back and calculated the class_weighting for my dataset for each class, and then it worked great.

@sandeepvr40 I think you need to change the ignore label. If you have 1 "target" class, you'll need a background class as well in addition to ignore, so depending on...

I'd like to second this. I'm having the exact same error.