In [1]:

    

%pylab inline
import pandas as pd
from keras import layers, models, metrics, optimizers, preprocessing, losses, regularizers
from keras.preprocessing import sequence
import regex
import re
from gensim.models import Word2Vec
from collections import Counter
from sklearn.feature_extraction.stop_words import ENGLISH_STOP_WORDS
from sklearn.model_selection import train_test_split


    

    




Populating the interactive namespace from numpy and matplotlib






    




Using TensorFlow backend.

In [2]:

    

df_all = pd.read_csv(open('training.1600000.processed.noemoticon.csv', encoding='ascii', errors='ignore'), header=None, 
                       names=['pol', 'id', 'date', 'lyx', 'user', 'txt']).append( # Latin-1 is a hack
           pd.read_csv('testdata.manual.2009.06.14.csv', header=None, 
                       names=['pol', 'id', 'date', 'lyx', 'user', 'txt']))
n_train = 1600000
n_test = df_all.shape[0] - n_train


    

In [3]:

    

df_all = df_all.loc[df_all.pol != 2]
df_all.pol = (df_all.pol == 4)


    

In [4]:

    

n_train = 1600000
n_test = df_all.shape[0] - n_train


    

In [5]:

    

date_re = re.compile(r'(?P<week_day>\w{3}) (?P<month>\w{3}) (?P<day>\d\d) (?P<hour>\d\d):(?P<minute>\d\d):(?P<second>\d\d) (?P<tz>\w{3}) (?P<year>\d{4})')


    

In [6]:

    

df_all[['week_day', 'day', 'hour']] = \
    df_all.date.str.extract(date_re, expand=True).loc[:,['week_day', 'day', 'hour']]


    

In [7]:

    

df_all = pd.get_dummies(df_all, columns=['week_day', 'day', 'hour'])


    

In [8]:

    

import regex
df_all.txt = (df_all.txt
              .str.replace(r'https?:\/\/\S+\b|www\.(\w+\.)+\S*', r' <URL> ')
              .str.replace(r'@\w*', r' <USER> ')
              .str.replace(r'#([A-Z0-9\-]+)', r' <HASHTAG> \1 <ALLCAPS> ')
              .str.replace(r'#(\S+)', lambda x: ' <HASHTAG> ' + ' '.join(regex.split(r'(?=[A-Z])', x.group(1))))
              .str.replace(r'<3', r' <HEART> ')
              .str.replace(r'([!?.]){2,}', r' \1 <REPEAT> ')
              .str.replace(r'\b(\S*?)(.)\2{2,}\b', r' \1\2 <ELONG> ')
              .str.replace(r'\s([^a-z0-9()<>\'`\-]){2,}\s',
                           lambda x: x.group(0).lower() + '<ALLCAPS> ')).str.lower()


    

In [23]:

    

df_test = df_all[n_train:].copy()
df_train = df_all[:n_train].copy()
del df_all


    

In [24]:

    

df_train = df_train.loc[np.random.permutation(df_train.shape[0])]


    

In [25]:

    

split_re = re.compile(r'[^\w<>]')


    

In [26]:

    

words = Counter(re.split(split_re, df_train.txt.str.cat(sep=' ')))


    

In [29]:

    

word_num = {word: i + 1 for word, i in words.most_common(20002)}


    

In [31]:

    

def convert_txt(df):
    tweets = []
    for tweet in df.txt:
        current_tweet_list = []
        for word in re.split(split_re, tweet):
            if word not in word_num or words[word] < 5:
                continue
            else:
                current_tweet_list.append(word_num[word])
        tweets.append(np.array(current_tweet_list))
    return tweets


    

In [32]:

    

maxlen = 60


    

In [33]:

    

X_train = sequence.pad_sequences(convert_txt(df_train), maxlen=maxlen, padding='post')


    

In [34]:

    

X_test = sequence.pad_sequences(convert_txt(df_test), maxlen=maxlen, padding='post')


    

In [38]:

    

y_test = df_test.pol


    

In [39]:

    

y_train = df_train.pol


    

In [40]:

    

X_train, X_cv, y_train, y_cv = train_test_split(
    X_train, y_train, test_size=.1)


    

In [41]:

    

np.mean(np.count_nonzero(X_train, axis=1))


    

    
Out[41]:





14.097610416666667

In [42]:

    

tweet = layers.Input((maxlen,), dtype='int32')


    

In [157]:

    

embedded = layers.Embedding(20002, 128, input_length=maxlen,)(tweet)


    

In [158]:

    

embedded_normalized = layers.Dropout(.5)(embedded)


    

In [159]:

    

conv1 = layers.Convolution1D(256, 5, padding='same', activation='relu')(embedded_normalized)


    

In [160]:

    

conv1_dropout = layers.BatchNormalization()(conv1)


    

In [161]:

    

conv2 = layers.Convolution1D(256, 4, padding='same', activation='relu')(conv1_dropout)


    

In [162]:

    

conv2_dropout = layers.BatchNormalization()(conv2)


    

In [168]:

    

lstm = layers.Bidirectional(layers.LSTM(16, recurrent_dropout=.3))(conv2_dropout)


    

In [169]:

    

lstm_dropout = layers.BatchNormalization()(lstm)


    

In [170]:

    

result = layers.Dense(1, activation='sigmoid', kernel_regularizer=regularizers.l2(1e-3))(lstm_dropout)


    

In [171]:

    

model = models.Model(tweet, result)


    

In [172]:

    

model.load_weights('conv-conv-bidirlstm.model')


    

In [31]:

    

model.compile(optimizer=optimizers.Adam(lr=1e-3), loss=losses.binary_crossentropy, metrics=['accuracy'])


    

In [45]:

    

model.fit(X_train, y_train, epochs=20, batch_size=256, 
          validation_data=(X_cv, y_cv))


    

    




Train on 1440000 samples, validate on 160000 samples
Epoch 1/20
1440000/1440000 [==============================] - 1215s - loss: 0.3590 - acc: 0.8415 - val_loss: 0.3339 - val_acc: 0.8546
Epoch 2/20
1440000/1440000 [==============================] - 1213s - loss: 0.3586 - acc: 0.8417 - val_loss: 0.3361 - val_acc: 0.8533
Epoch 3/20
1440000/1440000 [==============================] - 1200s - loss: 0.3578 - acc: 0.8421 - val_loss: 0.3389 - val_acc: 0.8522
Epoch 4/20
1440000/1440000 [==============================] - 1196s - loss: 0.3573 - acc: 0.8424 - val_loss: 0.3401 - val_acc: 0.8518
Epoch 5/20
   6144/1440000 [..............................] - ETA: 1165s - loss: 0.3608 - acc: 0.8381





    





KeyboardInterruptTraceback (most recent call last)
<ipython-input-45-b50908686898> in <module>()
      1 model.fit(X_train, y_train, epochs=20, batch_size=256, 
----> 2           validation_data=(X_cv, y_cv))

/usr/local/lib/python2.7/dist-packages/keras/engine/training.pyc in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, **kwargs)
   1484                               val_f=val_f, val_ins=val_ins, shuffle=shuffle,
   1485                               callback_metrics=callback_metrics,
-> 1486                               initial_epoch=initial_epoch)
   1487 
   1488     def evaluate(self, x, y, batch_size=32, verbose=1, sample_weight=None):

/usr/local/lib/python2.7/dist-packages/keras/engine/training.pyc in _fit_loop(self, f, ins, out_labels, batch_size, epochs, verbose, callbacks, val_f, val_ins, shuffle, callback_metrics, initial_epoch)
   1139                 batch_logs['size'] = len(batch_ids)
   1140                 callbacks.on_batch_begin(batch_index, batch_logs)
-> 1141                 outs = f(ins_batch)
   1142                 if not isinstance(outs, list):
   1143                     outs = [outs]

/usr/local/lib/python2.7/dist-packages/keras/backend/tensorflow_backend.pyc in __call__(self, inputs)
   2101         session = get_session()
   2102         updated = session.run(self.outputs + [self.updates_op],
-> 2103                               feed_dict=feed_dict)
   2104         return updated[:len(self.outputs)]
   2105 

/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.pyc in run(self, fetches, feed_dict, options, run_metadata)
    765     try:
    766       result = self._run(None, fetches, feed_dict, options_ptr,
--> 767                          run_metadata_ptr)
    768       if run_metadata:
    769         proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)

/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.pyc in _run(self, handle, fetches, feed_dict, options, run_metadata)
    963     if final_fetches or final_targets:
    964       results = self._do_run(handle, final_targets, final_fetches,
--> 965                              feed_dict_string, options, run_metadata)
    966     else:
    967       results = []

/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.pyc in _do_run(self, handle, target_list, fetch_list, feed_dict, options, run_metadata)
   1013     if handle is None:
   1014       return self._do_call(_run_fn, self._session, feed_dict, fetch_list,
-> 1015                            target_list, options, run_metadata)
   1016     else:
   1017       return self._do_call(_prun_fn, self._session, handle, feed_dict,

/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.pyc in _do_call(self, fn, *args)
   1020   def _do_call(self, fn, *args):
   1021     try:
-> 1022       return fn(*args)
   1023     except errors.OpError as e:
   1024       message = compat.as_text(e.message)

/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.pyc in _run_fn(session, feed_dict, fetch_list, target_list, options, run_metadata)
   1002         return tf_session.TF_Run(session, options,
   1003                                  feed_dict, fetch_list, target_list,
-> 1004                                  status, run_metadata)
   1005 
   1006     def _prun_fn(session, handle, feed_dict, fetch_list):

KeyboardInterrupt: 

In [33]:

    

model.load_weights('lstm-glove.model')


    

In [ ]:

    

import keras.


    

In [34]:

    

model.history.history


    

    
Out[34]:





{}

In [173]:

    

y_pred = model.predict(X_test, batch_size=256, verbose=1)


    

    




---------------------------------------------------------------------------
InvalidArgumentError                      Traceback (most recent call last)
~/twitter-sentiment/venv/lib/python3.6/site-packages/tensorflow/python/client/session.py in _do_call(self, fn, *args)
   1326     try:
-> 1327       return fn(*args)
   1328     except errors.OpError as e:

~/twitter-sentiment/venv/lib/python3.6/site-packages/tensorflow/python/client/session.py in _run_fn(session, feed_dict, fetch_list, target_list, options, run_metadata)
   1305                                    feed_dict, fetch_list, target_list,
-> 1306                                    status, run_metadata)
   1307 

/usr/local/Cellar/python3/3.6.3/Frameworks/Python.framework/Versions/3.6/lib/python3.6/contextlib.py in __exit__(self, type, value, traceback)
     87             try:
---> 88                 next(self.gen)
     89             except StopIteration:

~/twitter-sentiment/venv/lib/python3.6/site-packages/tensorflow/python/framework/errors_impl.py in raise_exception_on_not_ok_status()
    465           compat.as_text(pywrap_tensorflow.TF_Message(status)),
--> 466           pywrap_tensorflow.TF_GetCode(status))
    467   finally:

InvalidArgumentError: indices[1,8] = 68944 is not in [0, 20002)
	 [[Node: embedding_6/Gather = Gather[Tindices=DT_INT32, Tparams=DT_FLOAT, validate_indices=true, _device="/job:localhost/replica:0/task:0/cpu:0"](embedding_6/embeddings/read, _arg_input_1_0_1)]]

During handling of the above exception, another exception occurred:

InvalidArgumentError                      Traceback (most recent call last)
<ipython-input-173-0dea190b8404> in <module>()
----> 1 y_pred = model.predict(X_test, batch_size=256, verbose=1)

~/twitter-sentiment/venv/lib/python3.6/site-packages/keras/engine/training.py in predict(self, x, batch_size, verbose, steps)
   1711         f = self.predict_function
   1712         return self._predict_loop(f, ins, batch_size=batch_size,
-> 1713                                   verbose=verbose, steps=steps)
   1714 
   1715     def train_on_batch(self, x, y,

~/twitter-sentiment/venv/lib/python3.6/site-packages/keras/engine/training.py in _predict_loop(self, f, ins, batch_size, verbose, steps)
   1267                 else:
   1268                     ins_batch = _slice_arrays(ins, batch_ids)
-> 1269                 batch_outs = f(ins_batch)
   1270                 if not isinstance(batch_outs, list):
   1271                     batch_outs = [batch_outs]

~/twitter-sentiment/venv/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py in __call__(self, inputs)
   2271         updated = session.run(self.outputs + [self.updates_op],
   2272                               feed_dict=feed_dict,
-> 2273                               **self.session_kwargs)
   2274         return updated[:len(self.outputs)]
   2275 

~/twitter-sentiment/venv/lib/python3.6/site-packages/tensorflow/python/client/session.py in run(self, fetches, feed_dict, options, run_metadata)
    893     try:
    894       result = self._run(None, fetches, feed_dict, options_ptr,
--> 895                          run_metadata_ptr)
    896       if run_metadata:
    897         proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)

~/twitter-sentiment/venv/lib/python3.6/site-packages/tensorflow/python/client/session.py in _run(self, handle, fetches, feed_dict, options, run_metadata)
   1122     if final_fetches or final_targets or (handle and feed_dict_tensor):
   1123       results = self._do_run(handle, final_targets, final_fetches,
-> 1124                              feed_dict_tensor, options, run_metadata)
   1125     else:
   1126       results = []

~/twitter-sentiment/venv/lib/python3.6/site-packages/tensorflow/python/client/session.py in _do_run(self, handle, target_list, fetch_list, feed_dict, options, run_metadata)
   1319     if handle is None:
   1320       return self._do_call(_run_fn, self._session, feeds, fetches, targets,
-> 1321                            options, run_metadata)
   1322     else:
   1323       return self._do_call(_prun_fn, self._session, handle, feeds, fetches)

~/twitter-sentiment/venv/lib/python3.6/site-packages/tensorflow/python/client/session.py in _do_call(self, fn, *args)
   1338         except KeyError:
   1339           pass
-> 1340       raise type(e)(node_def, op, message)
   1341 
   1342   def _extend_graph(self):

InvalidArgumentError: indices[1,8] = 68944 is not in [0, 20002)
	 [[Node: embedding_6/Gather = Gather[Tindices=DT_INT32, Tparams=DT_FLOAT, validate_indices=true, _device="/job:localhost/replica:0/task:0/cpu:0"](embedding_6/embeddings/read, _arg_input_1_0_1)]]

Caused by op 'embedding_6/Gather', defined at:
  File "/usr/local/Cellar/python3/3.6.3/Frameworks/Python.framework/Versions/3.6/lib/python3.6/runpy.py", line 193, in _run_module_as_main
    "__main__", mod_spec)
  File "/usr/local/Cellar/python3/3.6.3/Frameworks/Python.framework/Versions/3.6/lib/python3.6/runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "/Users/pshevchuk/twitter-sentiment/venv/lib/python3.6/site-packages/ipykernel_launcher.py", line 16, in <module>
    app.launch_new_instance()
  File "/Users/pshevchuk/twitter-sentiment/venv/lib/python3.6/site-packages/traitlets/config/application.py", line 658, in launch_instance
    app.start()
  File "/Users/pshevchuk/twitter-sentiment/venv/lib/python3.6/site-packages/ipykernel/kernelapp.py", line 477, in start
    ioloop.IOLoop.instance().start()
  File "/Users/pshevchuk/twitter-sentiment/venv/lib/python3.6/site-packages/zmq/eventloop/ioloop.py", line 177, in start
    super(ZMQIOLoop, self).start()
  File "/Users/pshevchuk/twitter-sentiment/venv/lib/python3.6/site-packages/tornado/ioloop.py", line 888, in start
    handler_func(fd_obj, events)
  File "/Users/pshevchuk/twitter-sentiment/venv/lib/python3.6/site-packages/tornado/stack_context.py", line 277, in null_wrapper
    return fn(*args, **kwargs)
  File "/Users/pshevchuk/twitter-sentiment/venv/lib/python3.6/site-packages/zmq/eventloop/zmqstream.py", line 440, in _handle_events
    self._handle_recv()
  File "/Users/pshevchuk/twitter-sentiment/venv/lib/python3.6/site-packages/zmq/eventloop/zmqstream.py", line 472, in _handle_recv
    self._run_callback(callback, msg)
  File "/Users/pshevchuk/twitter-sentiment/venv/lib/python3.6/site-packages/zmq/eventloop/zmqstream.py", line 414, in _run_callback
    callback(*args, **kwargs)
  File "/Users/pshevchuk/twitter-sentiment/venv/lib/python3.6/site-packages/tornado/stack_context.py", line 277, in null_wrapper
    return fn(*args, **kwargs)
  File "/Users/pshevchuk/twitter-sentiment/venv/lib/python3.6/site-packages/ipykernel/kernelbase.py", line 283, in dispatcher
    return self.dispatch_shell(stream, msg)
  File "/Users/pshevchuk/twitter-sentiment/venv/lib/python3.6/site-packages/ipykernel/kernelbase.py", line 235, in dispatch_shell
    handler(stream, idents, msg)
  File "/Users/pshevchuk/twitter-sentiment/venv/lib/python3.6/site-packages/ipykernel/kernelbase.py", line 399, in execute_request
    user_expressions, allow_stdin)
  File "/Users/pshevchuk/twitter-sentiment/venv/lib/python3.6/site-packages/ipykernel/ipkernel.py", line 196, in do_execute
    res = shell.run_cell(code, store_history=store_history, silent=silent)
  File "/Users/pshevchuk/twitter-sentiment/venv/lib/python3.6/site-packages/ipykernel/zmqshell.py", line 533, in run_cell
    return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
  File "/Users/pshevchuk/twitter-sentiment/venv/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2728, in run_cell
    interactivity=interactivity, compiler=compiler, result=result)
  File "/Users/pshevchuk/twitter-sentiment/venv/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2850, in run_ast_nodes
    if self.run_code(code, result):
  File "/Users/pshevchuk/twitter-sentiment/venv/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2910, in run_code
    exec(code_obj, self.user_global_ns, self.user_ns)
  File "<ipython-input-157-d44e3f9d87cb>", line 1, in <module>
    embedded = layers.Embedding(20002, 128, input_length=maxlen,)(tweet)
  File "/Users/pshevchuk/twitter-sentiment/venv/lib/python3.6/site-packages/keras/engine/topology.py", line 602, in __call__
    output = self.call(inputs, **kwargs)
  File "/Users/pshevchuk/twitter-sentiment/venv/lib/python3.6/site-packages/keras/layers/embeddings.py", line 134, in call
    out = K.gather(self.embeddings, inputs)
  File "/Users/pshevchuk/twitter-sentiment/venv/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py", line 1134, in gather
    return tf.gather(reference, indices)
  File "/Users/pshevchuk/twitter-sentiment/venv/lib/python3.6/site-packages/tensorflow/python/ops/array_ops.py", line 2409, in gather
    validate_indices=validate_indices, name=name)
  File "/Users/pshevchuk/twitter-sentiment/venv/lib/python3.6/site-packages/tensorflow/python/ops/gen_array_ops.py", line 1219, in gather
    validate_indices=validate_indices, name=name)
  File "/Users/pshevchuk/twitter-sentiment/venv/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 767, in apply_op
    op_def=op_def)
  File "/Users/pshevchuk/twitter-sentiment/venv/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 2630, in create_op
    original_op=self._default_original_op, op_def=op_def)
  File "/Users/pshevchuk/twitter-sentiment/venv/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1204, in __init__
    self._traceback = self._graph._extract_stack()  # pylint: disable=protected-access

InvalidArgumentError (see above for traceback): indices[1,8] = 68944 is not in [0, 20002)
	 [[Node: embedding_6/Gather = Gather[Tindices=DT_INT32, Tparams=DT_FLOAT, validate_indices=true, _device="/job:localhost/replica:0/task:0/cpu:0"](embedding_6/embeddings/read, _arg_input_1_0_1)]]

In [47]:

    

X_test[0]


    

    
Out[47]:





array([  14165,  847053, 1050169,  464094,  330482,  677694,  733354,
        889739,  992092, 1050169,  626053, 1095865,   32850,  889739,
        626053,  828915,  626066,  729819,  484095,  545272,       0,
             0,       0,       0,       0,       0,       0,       0,
             0,       0,       0,       0,       0,       0,       0,
             0,       0,       0,       0,       0,       0,       0,
             0,       0,       0,       0,       0,       0,       0,
             0,       0,       0,       0,       0,       0,       0,
             0,       0,       0,       0], dtype=int32)

In [48]:

    

from sklearn import metrics


    

In [49]:

    

metrics.accuracy_score(y_test, y_pred > .5)


    

    
Out[49]:





0.84679665738161558

In [50]:

    

metrics.roc_auc_score(y_test, y_pred)


    

    
Out[50]:





0.92621220587322273

In [44]:

    

y_pred = model.predict(X_test, batch_size=256)
print metrics.roc_auc_score(y_test, y_pred)
print metrics.accuracy_score(y_test, y_pred > .5)


    

    




0.930371887999
0.844011142061

In [ ]:

    

print "OK"


    

In [51]:

    

model.save_weights('lstm-glove.model.new')


    

In [64]:

    

df_train.shape


    

    
Out[64]:





(1600000, 67)

In [65]:

    

X_train.shape


    

    
Out[65]:





(1440000, 60)

In [66]:

    

X_cv.shape


    

    
Out[66]:





(160000, 60)

In [35]:

    

%clear


    

In [37]:

    

%clear all


    

In [70]:

    

import h5py


    

In [71]:

    

f = h5py.File('conv-conv-bidirlstm.model', 'r')


    

In [78]:

    

list(f.attrs.keys())


    

    
Out[78]:





['layer_names', 'backend', 'keras_version']

In [80]:

    

f.attrs['layer_names']


    

    
Out[80]:





array([b'input_13', b'embedding_7', b'dropout_11', b'conv1d_13',
       b'batch_normalization_16', b'conv1d_14', b'batch_normalization_17',
       b'bidirectional_3', b'batch_normalization_18', b'dense_25'],
      dtype='|S22')

In [91]:

    

filtered_layers = [layer for layer in model.layers if getattr(layers, 'weights', None)]


    

In [92]:

    

filtered_layers


    

    
Out[92]:





[]

In [132]:

    

filtered_layers = []
for layer in model.layers:
    weights = layer.weights
    if weights:
        filtered_layers.append(layer)


    

In [133]:

    

filtered_layers


    

    
Out[133]:





[<keras.layers.embeddings.Embedding at 0x120e05390>,
 <keras.layers.convolutional.Conv1D at 0x120e1e438>,
 <keras.layers.normalization.BatchNormalization at 0x120773710>,
 <keras.layers.convolutional.Conv1D at 0x120e10c18>,
 <keras.layers.normalization.BatchNormalization at 0x120e100f0>,
 <keras.layers.wrappers.Bidirectional at 0x120e285c0>,
 <keras.layers.normalization.BatchNormalization at 0x1204a6cc0>,
 <keras.layers.core.Dense at 0x1213eb898>]

In [127]:

    

layer_names = [n.decode('utf8') for n in f.attrs['layer_names']]
filtered_layer_names = []
for name in layer_names:
    g = f[name]
    weight_names = [n.decode('utf8') for n in g.attrs['weight_names']]
    if weight_names:
        filtered_layer_names.append(name)


    

In [128]:

    

filtered_layer_names


    

    
Out[128]:





['embedding_7',
 'conv1d_13',
 'batch_normalization_16',
 'conv1d_14',
 'batch_normalization_17',
 'bidirectional_3',
 'batch_normalization_18',
 'dense_25']

In [108]:

    

for k, name in enumerate(filtered_layer_names):
    g = f[name]
    weight_names = [n.decode('utf8') for n in g.attrs['weight_names']]
    weight_values = [g[weight_name] for weight_name in weight_names]
    print(name, weight_values)


    

    




embedding_7 [<HDF5 dataset "embeddings:0": shape (20002, 128), type "<f4">]
conv1d_13 [<HDF5 dataset "kernel:0": shape (5, 128, 256), type "<f4">, <HDF5 dataset "bias:0": shape (256,), type "<f4">]
batch_normalization_16 [<HDF5 dataset "gamma:0": shape (256,), type "<f4">, <HDF5 dataset "beta:0": shape (256,), type "<f4">, <HDF5 dataset "moving_mean:0": shape (256,), type "<f4">, <HDF5 dataset "moving_variance:0": shape (256,), type "<f4">]
conv1d_14 [<HDF5 dataset "kernel:0": shape (4, 256, 256), type "<f4">, <HDF5 dataset "bias:0": shape (256,), type "<f4">]
batch_normalization_17 [<HDF5 dataset "gamma:0": shape (256,), type "<f4">, <HDF5 dataset "beta:0": shape (256,), type "<f4">, <HDF5 dataset "moving_mean:0": shape (256,), type "<f4">, <HDF5 dataset "moving_variance:0": shape (256,), type "<f4">]
bidirectional_3 [<HDF5 dataset "kernel:0": shape (256, 64), type "<f4">, <HDF5 dataset "recurrent_kernel:0": shape (16, 64), type "<f4">, <HDF5 dataset "bias:0": shape (64,), type "<f4">, <HDF5 dataset "kernel:0": shape (256, 64), type "<f4">, <HDF5 dataset "recurrent_kernel:0": shape (16, 64), type "<f4">, <HDF5 dataset "bias:0": shape (64,), type "<f4">]
batch_normalization_18 [<HDF5 dataset "gamma:0": shape (32,), type "<f4">, <HDF5 dataset "beta:0": shape (32,), type "<f4">, <HDF5 dataset "moving_mean:0": shape (32,), type "<f4">, <HDF5 dataset "moving_variance:0": shape (32,), type "<f4">]
dense_25 [<HDF5 dataset "kernel:0": shape (32, 1), type "<f4">, <HDF5 dataset "bias:0": shape (1,), type "<f4">]

In [120]:

    

from keras.engine.topology import preprocess_weights_for_loading


    

In [124]:

    

original_keras_version = f.attrs['keras_version'].decode('utf8')
original_backend = f.attrs['backend'].decode('utf8')


    

In [134]:

    

for k, name in enumerate(filtered_layer_names):
        g = f[name]
        weight_names = [n.decode('utf8') for n in g.attrs['weight_names']]
        weight_values = [g[weight_name] for weight_name in weight_names]
        print(k)
        layer = filtered_layers[k]
        symbolic_weights = layer.weights
        try:
            weight_values = preprocess_weights_for_loading(layer,
                                                           weight_values,
                                                           original_keras_version,
                                                           original_backend)
        except Exception as e:
            print(name, 'failed')


    

    




0
1
conv1d_13 failed
2
3
4
5
6
7

In [ ]:

    

fil