MonoDepth-FPN-PyTorch icon indicating copy to clipboard operation
MonoDepth-FPN-PyTorch copied to clipboard

what is the setting of the param :DOUBLE_BIAS and WEIGHT_DECAY

Open Usernamezhx opened this issue 5 years ago • 4 comments

First of all. thanks for your code. I don't know the setting about hte param : DOUBLE_BIAS and WEIGHT_DECAY . it show me that:

[epoch 0][iter 10] loss: nan RMSElog: nan grad_loss: nan normal_loss: nan [epoch 0][iter 20] loss: nan RMSElog: nan grad_loss: nan normal_loss: nan [epoch 0][iter 30] loss: nan RMSElog: nan grad_loss: nan normal_loss: nan [epoch 0][iter 40] loss: nan RMSElog: nan grad_loss: nan normal_loss: nan [epoch 0][iter 50] loss: nan RMSElog: nan grad_loss: nan normal_loss: nan [epoch 0][iter 60] loss: nan RMSElog: nan grad_loss: nan normal_loss: nan [epoch 0][iter 70] loss: nan RMSElog: nan grad_loss: nan normal_loss: nan

Usernamezhx avatar Dec 07 '18 03:12 Usernamezhx

I find the depth loss is inf.

Usernamezhx avatar Dec 07 '18 05:12 Usernamezhx

I find the question. because I use my own data. and the data has some zero value .So when I use the torch.log function. it will produce the inf value.

Usernamezhx avatar Dec 07 '18 05:12 Usernamezhx

what number you set about the DOUBLE_BIAS and WEIGHT_DECAY?

Haiyan-Chris-Wang avatar Oct 22 '19 20:10 Haiyan-Chris-Wang

what number you set about the DOUBLE_BIAS and WEIGHT_DECAY?

vinojhosan avatar Apr 03 '20 04:04 vinojhosan