CommissarMa
commented
5 years ago i think 1024 to 512 may not have much effect.
---Original--- From: "yxxxxxxxx"<notifications@github.com> Date: Sat, Sep 28, 2019 18:51 PM To: "CommissarMa/Context-Aware_Crowd_Counting-pytorch"<Context-Aware_Crowd_Counting-pytorch@noreply.github.com>; Cc: "Subscribed"<subscribed@noreply.github.com>; Subject: [CommissarMa/Context-Aware_Crowd_Counting-pytorch] Model Difference (#18)
Hello, thank you for your implements for Part_A dataset. I notice that there are some little differences between your model(cannet.py) and the official https://github.com/weizheliu/Context-Aware-Crowd-Counting/blob/master/model.py The official code add one convolution layer to reduce channel numbers from 1024 to 512 before sending feature maps into backend, but you input it without any other operations. I wonder if this way works better or for some other reasons. Thank you!
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub, or mute the thread.
Hello, thank you for your implements for Part_A dataset. I notice that there are some little differences between your model(cannet.py) and the official https://github.com/weizheliu/Context-Aware-Crowd-Counting/blob/master/model.py The official code add one convolution layer to reduce channel numbers from 1024 to 512 before sending feature maps into backend, but you input it without any other operations. I wonder if this way works better or for some other reasons. Thank you!