search

svishwa / crowdcount-mcnn

Single Image Crowd Counting via MCNN (Unofficial Implementation)
MIT License
499 stars 179 forks source link

Do I need to pretrain? #19

Open 1shan1 opened 6 years ago

1shan1 commented 6 years ago

I rewrite it in caffe,but I can not get that good results,in your code ,when I use epoch 0 model to test,MSE can reach 445,while mine in caffe epoch 0 model is 11535.Have you use pretrain??

svishwa commented 6 years ago

The authors in the paper suggested pre-training. However, I did not do pre-training.