haofengac / MonoDepth-FPN-PyTorch

Single Image Depth Estimation with Feature Pyramid Network
MIT License
327 stars 69 forks source link

what is the setting of the param :DOUBLE_BIAS and WEIGHT_DECAY #13

Open Usernamezhx opened 5 years ago

Usernamezhx commented 5 years ago

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 commented 5 years ago

I find the depth loss is inf.

Usernamezhx commented 5 years ago

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.

Haiyan-Chris-Wang commented 5 years ago

what number you set about the DOUBLE_BIAS and WEIGHT_DECAY?

vinojhosan commented 4 years ago

what number you set about the DOUBLE_BIAS and WEIGHT_DECAY?