CSRNet-pytorch
CSRNet-pytorch copied to clipboard
CommissarMa
Implementation of WorldExpo'10 dataset
Hi, I'm using CSRNet for crowd counting on world Expo'10 dataset. However, I cannot reproduce the results of the paper(8.6 MAE), I only got a MAE around 10.2. Could you please provide the implementation of world Expo'10 dataset(e.g. density map generation or how to utilize the ROI and evalutation), or at least provide some implementation details( learning rate, batch size ect.). Thank you so much!!
sorry，I didn't conduct experiments on world expo. And only do it on Shanghaitech part a. but flip the image and upsample image can enhance the performance. the learning rate can vary from 1e-5 to 1e-7 to finetune the model gradually. decay is default.
---Original--- From: "Desen Zhou"<[email protected]> Date: Wed, Apr 8, 2020 14:18 PM To: "CommissarMa/CSRNet-pytorch"<[email protected]>; Cc: "Subscribed"<[email protected]>; Subject: [CommissarMa/CSRNet-pytorch] Implementation of WorldExpo'10 dataset (#4)
Hi, I'm using CSRNet for crowd counting on world Expo'10 dataset. However, I cannot reproduce the results of the paper(8.6 MAE), I only got a MAE around 10.2. Could you please provide the implementation of world Expo'10 dataset(e.g. density map generation or how to utilize the ROI and evalutation), or at least provide some implementation details( learning rate, batch size ect.). Thank you so much!!
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub, or unsubscribe.
Hi, I'm using CSRNet for crowd counting on world Expo'10 dataset. However, I cannot reproduce the results of the paper(8.6 MAE), I only got a MAE around 10.2. Could you please provide the implementation of world Expo'10 dataset(e.g. density map generation or how to utilize the ROI and evalutation), or at least provide some implementation details( learning rate, batch size ect.). Thank you so much!!
Hi, could you give me a download link about WorldExpo’10 Crowd Counting Dataset? I have send emails to [email protected], but I didn't get any reply. If you have the dataset, could you send download link to me ? My email is [email protected]. Thanks!
