age-estimation-pytorch icon indicating copy to clipboard operation
age-estimation-pytorch copied to clipboard

Published 20 hours ago • verified publisher icon yu4u

run problem

Open cliobeach opened this issue 5 years ago • 4 comments

when i run the code !python train.py --data_dir data_dir/appa-real-release --tensorboard tf_log MODEL.ARCH se_resnet50 TRAIN.OPT sgd TRAIN.LR 0.1

it has a response like : => creating model 'se_resnet50' 0% 0/31 [00:00<?, ?it/s]^C

can you tell me how to fix this please

cliobeach avatar Jun 30 '19 16:06 cliobeach

all ready fix it i just changed the sever

cliobeach avatar Jul 02 '19 03:07 cliobeach

Good. What was the problem?

yu4u avatar Jul 02 '19 03:07 yu4u

i not should , maybe because the memory problem i mentioned in the other issue.

cliobeach avatar Jul 03 '19 01:07 cliobeach

I get a terminated error with no start even, looks the same as yours, does it mean I need more powerful/GPU machine ?

/usr/local/lib/python3.8/site-packages/tensorboard/compat/tensorflow_stub/dtypes.py:550: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
  np_resource = np.dtype([("resource", np.ubyte, 1)])
=> creating model 'se_resnet50'
  0%|           | 0/31 [00:00<?, ?it/s]
Terminated

mirkobrankovic avatar May 02 '20 13:05 mirkobrankovic