Weights initialisation error

[lvaleriu]

I'm trying to reproduce the cBAD_complex training but I get the following error when running the run.sh script.

Have you already encountered it?

FYI: I have torch 1.3.1.

tf-docker ~/workspace/P2PaLA/egs/cBAD_complex > python ../../P2PaLA.py --config config.txt --log_comment "cBAD_corpus"
2019-11-29 11:05:33,786 - optparse - INFO - Reading configuration from config.txt
2019-11-29 11:05:33,800 - P2PaLA - INFO - Working on training stage...
2019-11-29 11:05:33,921 - P2PaLA - INFO - TensorBoard log will be stored at ./work/runs/Nov29_11-05-33_ABC_cBAD_corpus
2019-11-29 11:05:33,921 - P2PaLA - INFO - run: tensorboard --logdir ./work/runs
2019-11-29 11:05:33,921 - P2PaLA - INFO - Preprocessing data from data/train/
File cBAD_complex_train_109 do not contains baselines
File cBAD_complex_train_2 do not contains baselines
File cBAD_complex_train_244 do not contains baselines
File cBAD_complex_train_268 do not contains baselines
File cBAD_complex_train_80 do not contains baselines
File cBAD_complex_train_8 do not contains baselines
File cBAD_complex_train_39 do not contains baselines
File cBAD_complex_train_13 do not contains baselines
File cBAD_complex_train_111 do not contains baselines
File cBAD_complex_train_11 do not contains baselines
File cBAD_complex_train_7 do not contains baselines
File cBAD_complex_train_258 do not contains baselines
File cBAD_complex_train_10 do not contains baselines
File cBAD_complex_train_9 do not contains baselines
File cBAD_complex_train_27 do not contains baselines
File cBAD_complex_train_90 do not contains baselines
File cBAD_complex_train_22 do not contains baselines
File cBAD_complex_train_67 do not contains baselines
File cBAD_complex_train_245 do not contains baselines
File cBAD_complex_train_23 do not contains baselines
Traceback (most recent call last):
File "../../P2PaLA.py", line 1269, in
main()
File "../../P2PaLA.py", line 460, in main
nnG.apply(models.weights_init_normal)
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 287, in apply
module.apply(fn)
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 287, in apply
module.apply(fn)
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 287, in apply
module.apply(fn)
[Previous line repeated 2 more times]
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 288, in apply
fn(self)
File "/root/workspace/P2PaLA/nn_models/models.py", line 298, in weights_init_normal
nn.init.uniform(m.weight.data, 1.0, 0.02)
File "/usr/local/lib/python3.6/dist-packages/torch/nn/init.py", line 88, in uniform_
return no_grad_uniform(tensor, a, b)
File "/usr/local/lib/python3.6/dist-packages/torch/nn/init.py", line 14, in no_grad_uniform
return tensor.uniform_(a, b)
RuntimeError: uniform_ expects to return a [from, to) range, but found from=1 > to=0.02