princeton-vl / pytorch_stacked_hourglass

Pytorch implementation of the ECCV 2016 paper "Stacked Hourglass Networks for Human Pose Estimation"
BSD 3-Clause "New" or "Revised" License
465 stars 94 forks source link

Please help me? #42

Closed Deerzh closed 1 year ago

Deerzh commented 1 year ago

when I run this command: python train.py -e test_run_001 an error occurred, like this: Traceback (most recent call last): File "train.py", line 129, in main() File "train.py", line 125, in main train(func, data_func, config) File "train.py", line 96, in train outs = train_func(batch_id + i, config, phase, **datas) File "/home/zhang/compatibility_analysis/pytorch_stacked_hourglass/task/pose.py", line 140, in make_train for param_group in optimizer.param_groups: UnboundLocalError: local variable 'optimizer' referenced before assignment

I just modified 'train_iters': 1, 'valid_iters': 1, 'decay_iters': 1. Can you help me solved this problem?

crockwell commented 1 year ago

Apologies for the slow reply, I hope you have figured this out by now! In case you haven't:

It looks like optimizer was not initialized. Perhaps you have phase set to something other than "train", causing these few lines to be skipped?