search

xwjabc / hed

A PyTorch reimplementation of Holistically-Nested Edge Detection
170 stars 42 forks source link

its about DeepFashion2 #19

Open tomriddle54 opened 4 years ago

tomriddle54 commented 4 years ago

Sorry to write here about DeepFashion2 I was seeing your comments on DeepFashion2 you have trained model. Can you guide how to train DeepFashion2 I tried it but it was confusing.

xwjabc commented 4 years ago

Sorry to write here about DeepFashion2 I was seeing your comments on DeepFashion2 you have trained model. Can you guide how to train DeepFashion2 I tried it but it was confusing.

For the MatchNet baseline in DeepFashion2, I reimplement the model based on maskrcnn-benchmark. The coefficients of loss terms are set to 1. I will try to reorganize the code and release it a bit later. If you want to know more details, feel free to ask here.

tomriddle54 commented 4 years ago

@xwjabc thanks for the reply. I tried my way but the accuracy issue. I am waiting for your release code.

tomriddle54 commented 4 years ago

@xwjabc any update on your reimplement. how can i run deepfashion2_retrieval_test.py can you tell steps to run it.