andreamad8 / qdren Goto Github PK

mldl@mldlUB1604:/ub16_prj/QDREN/CNN$ python3 run_final.py
Traceback (most recent call last):
File "run_final.py", line 10, in
from src.utils.ulilz_CNN import Dataset
File "/home/mldl/ub16_prj/QDREN/CNN/src/utils/ulilz_CNN.py", line 2, in
import config
ImportError: No module named 'config'
mldl@mldlUB1604:/ub16_prj/QDREN/CNN$

mldl@mldlUB1604:/ub16_prj/QDREN/CNN$
mldl@mldlUB1604:/ub16_prj/QDREN/CNN$ PYTHONPATH=src python3 run_final.py
Traceback (most recent call last):
File "run_final.py", line 11, in
from src.trainer.train import train
File "/home/mldl/ub16_prj/QDREN/CNN/src/trainer/train.py", line 18, in
from data.email_util import send_email
ImportError: No module named 'data.email_util'
mldl@mldlUB1604:~/ub16_prj/QDREN/CNN$

https://nlp.stanford.edu/blog/a-new-multi-turn-multi-domain-task-oriented-dialogue-dataset/

        with open(ckpt_dir + "training_logs.pik", 'wb') as f:  #yknote for python3 error must be str, not bytes
            pickle.dump((train_loss, train_acc, val_loss, val_acc, test_loss, test_acc), f)

otherwise, it reports error 'must be str, not bytes'

mldl@mldlUB1604:/ub16_prj/QDREN/bAbI$ PYTHONPATH=src python3 run_final.py 15
/usr/local/lib/python3.5/dist-packages/sklearn/cross_validation.py:44: DeprecationWarning: This module was deprecated in version 0.18 in favor of the model_selection module into which all the refactored classes and functions are moved. Also note that the interface of the new CV iterators are different from that of this module. This module will be removed in 0.20.
"This module will be removed in 0.20.", DeprecationWarning)
/usr/local/lib/python3.5/dist-packages/sklearn/grid_search.py:43: DeprecationWarning: This module was deprecated in version 0.18 in favor of the model_selection module into which all the refactored classes and functions are moved. This module will be removed in 0.20.
DeprecationWarning)
08-07 23:14 Longest sentence length: 6
08-07 23:14 Longest story length: 8
08-07 23:14 Average story length: 8
08-07 23:14 Training sample: 900
08-07 23:14 Validation sample: 100
08-07 23:14 Test sample: 1000
08-07 23:14 Vocab size : 18
08-07 23:14 Embeddings: 18 x 100
08-07 23:14 Loading embedding file: data/glove.6B.100d.txt
08-07 23:14 Pre-trained: 17 (94.44%)
08-07 23:14 Parameters: 49000
08-07 23:14 Initializing Variables!
08-07 23:14 Training stated
08-07 23:14 Epoch 0 Train Loss: 4.137 Train Accuracy: 0.206
08-07 23:14 Start plotting
Traceback (most recent call last):
File "run_final.py", line 88, in
main(task_num=sys.argv[1])
File "run_final.py", line 64, in main
t = train(epoch,params['bz'], data, par, dr=params['dr'], _test=True)
File "/home/mldl/ub16_prj/QDREN/bAbI/src/trainer/train.py", line 128, in train
val_loss[e], val_acc[e] = val_test(all_val,'Validation')
File "/home/mldl/ub16_prj/QDREN/bAbI/src/trainer/train.py", line 85, in val_test
viz(e)
File "/home/mldl/ub16_prj/QDREN/bAbI/src/trainer/train.py", line 59, in viz
for i in range(l):
TypeError: only integer scalar arrays can be converted to a scalar index
mldl@mldlUB1604:/ub16_prj/QDREN/bAbI$
mldl@mldlUB1604:~/ub16_prj/QDREN/bAbI$