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

Lack of instructions

Open nikitadurasov opened this issue 5 years ago • 2 comments

Now I faced a couple of problems: there are no such modules as "constants", "utils" and etc, but its not a major problem. I'm trying to run main_fpn.py with python main_fpn.py --epochs 40 --cuda --bs 4 --num_workers 3 --output_dir output_dir/, but only got NaN's as output from network and as values of losses.

Could you please write more detailed instructions how to run your code?

nikitadurasov avatar Oct 11 '18 13:10 nikitadurasov

@NikitaDurasov do you solve the problem?

Usernamezhx avatar Dec 07 '18 03:12 Usernamezhx

Also here trying to "make it works"

For now: UTILS Comment from utils.net_utils import adjust_learning_rate to # from utils.net_utils import adjust_learning_rate

From https://github.com/jwyang/faster-rcnn.pytorch/blob/master/lib/model/utils/net_utils.py

Download the net_utils.py, or just define the adjust_learning_rate function

def adjust_learning_rate(optimizer, decay=0.1):
    """Sets the learning rate to the initial LR decayed by 0.5 every 20 epochs"""
    for param_group in optimizer.param_groups:
        param_group['lr'] = decay * param_group['lr']

agustincl avatar May 01 '19 12:05 agustincl