according to toy example, I run
python src/launcher.py --phase=train --data-path=sample/sample.txt --data-base-dir=sample --log-path=log.txt --no-load-model
it throw such error:
module 'tensorflow.contrib.rnn.python.ops.rnn_cell' has no attribute '_linear
then I modiify code according @masonsun in #71 ,it throw such error:
input_tensor dim: (?, 1, 32, ?)
CNN outdim before squeeze: (?, 1, ?, 512)
CNN outdim: (?, ?, 512)
Traceback (most recent call last):
File "src/launcher.py", line 146, in
main(sys.argv[1:], exp_config.ExpConfig)
File "src/launcher.py", line 142, in main
session = sess)
File "/home/gml/Documents/Attention-OCR/src/model/model.py", line 151, in init
use_gru = use_gru)
File "/home/gml/Documents/Attention-OCR/src/model/seq2seq_model.py", line 87, in init
single_cell = tf.contrib.rnn.core_rnn_cell.BasicLSTMCell(attn_num_hidden, forget_bias=0.0, state_is_tuple=False)
AttributeError: module 'tensorflow.contrib.rnn' has no attribute 'core_rnn_cell'
What should I do? I use tf with version of 1.12.0
according to toy example, I run python src/launcher.py --phase=train --data-path=sample/sample.txt --data-base-dir=sample --log-path=log.txt --no-load-model it throw such error: module 'tensorflow.contrib.rnn.python.ops.rnn_cell' has no attribute '_linear then I modiify code according @masonsun in #71 ,it throw such error: input_tensor dim: (?, 1, 32, ?) CNN outdim before squeeze: (?, 1, ?, 512) CNN outdim: (?, ?, 512) Traceback (most recent call last): File "src/launcher.py", line 146, in
main(sys.argv[1:], exp_config.ExpConfig)
File "src/launcher.py", line 142, in main
session = sess)
File "/home/gml/Documents/Attention-OCR/src/model/model.py", line 151, in init
use_gru = use_gru)
File "/home/gml/Documents/Attention-OCR/src/model/seq2seq_model.py", line 87, in init
single_cell = tf.contrib.rnn.core_rnn_cell.BasicLSTMCell(attn_num_hidden, forget_bias=0.0, state_is_tuple=False)
AttributeError: module 'tensorflow.contrib.rnn' has no attribute 'core_rnn_cell'
What should I do? I use tf with version of 1.12.0