search

abbypa / NNProject_DeepMask

Deep Neural Network for object segmentation.
187 stars 60 forks source link

EndToEnd.py can't find images #19

Closed recluze closed 7 years ago

recluze commented 7 years ago

I followed the steps given in the readme. Got some examples generated through ExampleGenerator.py. However, it seems that EndToEnd.py can't find them. Sifting through the code, I could gather that ExamplesGenerator.py is writing to Results/pos-train and Results/neg-train whereas EndToEnd.py is trying to read from Predictions/train. Is there a missing step in the readme where we need to move files to the correct folder or is there some other error?

(For details, the error I'm getting in EndToEnd.py is the empty list when trying to stack images.)

p.s. Thanks a lot for putting in the effort to make this code available and for pointing to the pre-trained models.

abbypa commented 7 years ago

Yes, you are correct- you should create a Predictions/train folder with the examples to train on. You can choose your own ratio of positive vs. negative examples. I'll add this to the readme file, thank you!

dav-sap commented 7 years ago

hey @abbypa Why would I want to use negative examples in my Predictions/Train folder? and how will the code know to learn that these are neg examples\pos examples?