search

s9xie / hed

code for Holistically-Nested Edge Detection
Other
1.79k stars 528 forks source link

although I was to use the learning rate of 1*10e-8, but the value of loss is very big #29

Open cchenzhou opened 7 years ago

cchenzhou commented 7 years ago

Hi, First of all thank you provide the project code generously. I'am trying to train the network on BSDS dataset. But the loss can not convergence. Then, I can understand the value of max_iter equals 30001,and the training process does't stop until iteration equals 100000. Any idea about how to fix the error? Thank you! chen

mhl20110088 commented 6 years ago

I have encountered the same problem,but I do not know how to modify it.I think ,you try to modify the loss layer of the network .

mengzhangjian commented 6 years ago

I also encounter the same problem , the initial loss is very large and does not converge ,anyone knows it ?

chaobeiying commented 6 years ago

Have you solved your problem?