xvbw

@jmydurant Thanks! I've checked out that site too before and guessed it would be a solution. That worked. Thanks again

Thanks! I've noticed you had a similar issue previously. Will try this and show the result

Yes, paste the code here please. That could be really helpful. Thanks. +plus, Is LFW annotation corrected by hand after flandmark algorithm performs its landmark detection or is it just...

Yeah! exactly. Actually, I solved this by changing `layer_type: PIXEL` to `layer_type: NONE` as you already mentioned. Thanks for the reply

@ksnzh I used CuDNN v4. You may have a GPU that is newer than `compute_35`. That's the reason it fails to run training with CuDNN. Glad you fixed it.

@ksnzh Can you name the missing files so that I can check if I have that file in my augmented VOC dataset. I have not trained on augmented VOC dataset...

`2007_006560` is from original VOC dataset. Not the augmented VOC dataset. You need to change the path of each original file or you can just merge original and augmented VOC...

That error occurs because the path of `2007_006560` is wrong. `train_val.txt` includes file lists of both original and augmented. But original and augmented VOC dataset are in the separate folder....