search

chenjun2hao / DDRNet.pytorch

This is the unofficial code of Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes. which achieve state-of-the-art trade-off between accuracy and speed on cityscapes and camvid, without using inference acceleration and extra data
Other
161 stars 41 forks source link

RuntimeError: value cannot be converted to type float without overflow: (3.32193e-07,-1.07936e-07) #16

Open huajng opened 2 years ago

huajng commented 2 years ago

how to solve this running error?

huajng commented 2 years ago

Traceback (most recent call last): File "tools/train.py", line 324, in main() File "tools/train.py", line 288, in main trainloader, optimizer, model, writer_dict) File "/nfs/home/huanghaiyang/data5/method2f/DDRNet.pytorch-main/tools/../lib/core/function.py", line 74, in train optimizer.step() File "/nfs/home/huanghaiyang/.conda/envs/52f/lib/python3.6/site-packages/torch/autograd/grad_mode.py", line 26, in decoratecontext return func(*args, **kwargs) File "/nfs/home/huanghaiyang/.conda/envs/52f/lib/python3.6/site-packages/torch/optim/sgd.py", line 112, in step p.add(d_p, alpha=-group['lr']) RuntimeError: value cannot be converted to type float without overflow: (3.32193e-07,-1.07936e-07) Traceback (most recent call last): File "/nfs/home/huanghaiyang/.conda/envs/52f/lib/python3.6/runpy.py", line 193, in _run_module_as_main "main", mod_spec) File "/nfs/home/huanghaiyang/.conda/envs/52f/lib/python3.6/runpy.py", line 85, in _run_code exec(code, run_globals) File "/nfs/home/huanghaiyang/.conda/envs/52f/lib/python3.6/site-packages/torch/distributed/launch.py", line 260, in main() File "/nfs/home/huanghaiyang/.conda/envs/52f/lib/python3.6/site-packages/torch/distributed/launch.py", line 256, in main cmd=cmd) subprocess.CalledProcessError: Command '['/nfs/home/huanghaiyang/.conda/envs/52f/bin/python', '-u', 'tools/train.py', '--local_rank=0', '--cfg', 'experiments/cityscapes/ddrnet23_slim.yaml']' returned non-zero exit status 1.