hi, can you give some ideas of how I can increase the words contained in the dictionary to add more cities?

Thanks!

rzai@rzai00:/prj/ATIS.keras$ python main.py
Using Theano backend.
Using gpu device 0: GeForce GTX 1080 (CNMeM is disabled)
atis.pkl
Traceback (most recent call last):
File "main.py", line 35, in
model.add(Convolution1D(64,5,border_mode='same', activation='relu'))
File "/usr/local/lib/python2.7/dist-packages/keras/models.py", line 308, in add
output_tensor = layer(self.outputs[0])
File "/usr/local/lib/python2.7/dist-packages/keras/engine/topology.py", line 514, in call
self.add_inbound_node(inbound_layers, node_indices, tensor_indices)
File "/usr/local/lib/python2.7/dist-packages/keras/engine/topology.py", line 572, in add_inbound_node
Node.create_node(self, inbound_layers, node_indices, tensor_indices)
File "/usr/local/lib/python2.7/dist-packages/keras/engine/topology.py", line 149, in create_node
output_tensors = to_list(outbound_layer.call(input_tensors[0], mask=input_masks[0]))
File "/usr/local/lib/python2.7/dist-packages/keras/layers/convolutional.py", line 158, in call
dim_ordering='tf')
File "/usr/local/lib/python2.7/dist-packages/keras/backend/theano_backend.py", line 1135, in conv2d
filter_shape=filter_shape)
File "/usr/local/lib/python2.7/dist-packages/theano/tensor/nnet/conv.py", line 149, in conv2d
imshp=imshp, kshp=kshp, nkern=nkern, bsize=bsize, **kargs)
TypeError: init() got an unexpected keyword argument 'input_shape'
rzai@rzai00:/prj/ATIS.keras$

When I execute: python main.py ,I got this error:

Using TensorFlow backend.
Traceback (most recent call last):
  File "main.py", line 19, in <module>
    train_set, valid_set, dicts = data.load.atisfull()
  File "/home/c1/gitcloned/ATIS.keras/data/load.py", line 51, in atisfull
    train_set, test_set, dicts = pickle.load(f)
EOFError: Ran out of input

How can I fix it ?
Please help me, thanks a lot!

Hey,
I get a ModuleNotFoundError while downloading the data.

`
import numpy as np
from data import load
train_set, valid_set, dicts = load.atisfull()

ModuleNotFoundError Traceback (most recent call last)
in ()
----> 1 train_set, valid_set, dicts = load.atisfull()

D:\mypath\atisfull_keras\ATIS.keras\data\load.py in atisfull()
49
50 try:
---> 51 train_set, test_set, dicts = pickle.load(f)
52 except UnicodeDecodeError:
53 train_set, test_set, dicts = pickle.load(f, encoding='latin1')

ModuleNotFoundError: No module named 'numpy.core.multiarray\r'
`

Is that my bad or should the \r not be there?

sysinfo:
System: 3.6.3 |Anaconda custom (64-bit)| (default, Nov 8 2017, 15:10:56) [MSC v.1900 64 bit (AMD64)]
Windows-10-10.0.16299-SP0

Hi, I'm having this error when loading the data, and I can't solve it:

UnpicklingError                           Traceback (most recent call last)
<ipython-input-13-d6cdf9258128> in <module>()
      2 import data.load
      3 
----> 4 train_set, valid_set, dicts = data.load.atisfull()
      5 w2idx, labels2idx = dicts['words2idx'], dicts['labels2idx']
      6 

/home/ec2-user/tf-notebook/query_intent_detection/slotfilling/data/load.pyc in atisfull()
     49 
     50     try:
---> 51         train_set, test_set, dicts = pickle.load(f)
     52     except UnicodeDecodeError:
     53         train_set, test_set, dicts = pickle.load(f, encoding='latin1')

UnpicklingError: invalid load key, '<'.

in your code:

def download_dropbox():
    ''' 
    download from drop box in the meantime
    '''
    print('Downloading data from https://www.dropbox.com/s/3lxl9jsbw0j7h8a/atis.pkl?dl=0')
    os.system('wget -O atis.pkl https://www.dropbox.com/s/3lxl9jsbw0j7h8a/atis.pkl?dl=0')

but this url has been lost.
can you provide a new link?
Thanks.

I am trying to use word2vec vector as input.

this is the original input

 1     ['我', '想', '看', '电影']
 2     ['有', '没有', '美剧']
 ...
 9999  ['有', '没有', '美剧']

replace words with the vector

 1     [[word2vec size=200], [word2vec size=200], [word2vec size=200], [word2vec size=200]]
 2     [[word2vec size=200], [word2vec size=200], [word2vec size=200]]
 ...
 9999  [[word2vec size=200], [word2vec size=200], [word2vec size=200]]

pan the vectors with np.zeros.

 1     [[word2vec size=200], [word2vec size=200], [word2vec size=200], [word2vec size=200], [word2vec size=200], [word2vec size=200]]
 2     [[word2vec size=200], [word2vec size=200], [word2vec size=200], [word2vec size=200], [word2vec size=200], [word2vec size=200]]
 ....
 9999  [[word2vec size=200], [word2vec size=200], [word2vec size=200], [word2vec size=200], [word2vec size=200], [word2vec size=200]]

Then use the result as input. Is this doable? and how should I do that? Thanks a lot.