Hello, Could you explain why do you define a loss function (cost) instead of using a pre-defined one in TFLearn?
Thanks!

PRE_EMB size 22518
max sentence size is : 30
Traceback (most recent call last):
File "NerMulti.py", line 213, in
X_train, y_train = get_input(BASE_DIR+"/eng.train")
File "NerMulti.py", line 125, in get_input
temp = np.append(temp,capital(line.split()[0])) # adding capital embedding
File "NerMulti.py", line 52, in capital
if ord(word[0]) >= 'A' and ord(word[0]) <= 'Z':
TypeError: unorderable types: int() >= str()

I am newbie to python.
How to resolve this error???

Traceback (most recent call last):
File "C:/Users/weihao/Desktop/NER-RNN-master/NerMulti.py", line 213, in
X_train, y_train = get_input(BASE_DIR+"/eng.train")
File "C:/Users/weihao/Desktop/NER-RNN-master/NerMulti.py", line 145, in get_input
return np.asarray(sentence), sentence_tag
File "D:\Anaconda3\envs\tensorflow\lib\site-packages\numpy\core\numeric.py", line 531, in asarray
return array(a, dtype, copy=False, order=order)
MemoryError

how to change？

Run id: IOM5G7
Log directory: /tmp/tflearn_logs/

Training samples: 14987
Validation samples: 3467

E tensorflow/core/util/events_writer.cc:62] Could not open events file: /tmp/tflearn_logs/IOM5G7/events.out.tfevents.1478962669.rzai00: Resource exhausted: /tmp/tflearn_logs/IOM5G7/events.out.tfevents.1478962669.rzai00h: 000 | loss: nan -- iter: 00200/14987
E tensorflow/core/util/events_writer.cc:95] Write failed because file could not be opened.
E tensorflow/core/util/events_writer.cc:62] Could not open events file: /tmp/tflearn_logs/IOM5G7/events.out.tfevents.1478962670.rzai00: Resource exhausted: /tmp/tflearn_logs/IOM5G7/events.out.tfevents.1478962670.rzai00h: 000 | loss: nan -- iter: 00400/14987
E tensorflow/core/util/events_writer.cc:95] Write failed because file could not be opened.

Can you please tell which tensorflow version have you used for your repo?
The current version as well as tensorflow==0.11.0 are giving many errors