I am trying to get code working from the following repo, which is based off this paper. It had a lot of errors, but I mostly got it working. However, I keep getting the same problem and I really do not understand how to troubleshoot this/what is even going wrong.
The error occurs the second time the validation if statement critera is met. The first time is always works, then breaks on the second. I'm including the output it prints before breaking if its helpful. See error below:
step = 1, train_loss = 1204.7784423828125, train_accuracy = 0.13725490868091583
counter = 1, dev_loss = 1188.6639287274584, dev_accuacy = 0.2814199453625912
step = 2, train_loss = 1000.983154296875, train_accuracy = 0.26249998807907104
---------------------------------------------------------------------------
InvalidArgumentError Traceback (most recent call last)
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/client/session.py in _do_call(self, fn, *args)
1364 try:
-> 1365 return fn(*args)
1366 except errors.OpError as e:
7 frames
InvalidArgumentError: 2 root error(s) found.
(0) Invalid argument: Incompatible shapes: [2,185] vs. [2,229]
[[{{node loss/cond/add_1}}]]
[[viterbi_decode/cond/rnn_1/while/Switch_3/_541]]
(1) Invalid argument: Incompatible shapes: [2,185] vs. [2,229]
[[{{node loss/cond/add_1}}]]
0 successful operations.
0 derived errors ignored.
During handling of the above exception, another exception occurred:
InvalidArgumentError Traceback (most recent call last)
/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/client/session.py in _do_call(self, fn, *args)
1382 '\nsession_config.graph_options.rewrite_options.'
1383 'disable_meta_optimizer = True')
-> 1384 raise type(e)(node_def, op, message)
1385
1386 def _extend_graph(self):
InvalidArgumentError: 2 root error(s) found.
(0) Invalid argument: Incompatible shapes: [2,185] vs. [2,229]
[[node loss/cond/add_1 (defined at /usr/local/lib/python3.6/dist-packages/tensorflow_core/python/framework/ops.py:1748) ]]
[[viterbi_decode/cond/rnn_1/while/Switch_3/_541]]
(1) Invalid argument: Incompatible shapes: [2,185] vs. [2,229]
[[node loss/cond/add_1 (defined at /usr/local/lib/python3.6/dist-packages/tensorflow_core/python/framework/ops.py:1748) ]]
0 successful operations.
0 derived errors ignored.
Original stack trace for 'loss/cond/add_1':
File "/usr/lib/python3.6/runpy.py", line 193, in _run_module_as_main
"__main__", mod_spec)
File "/usr/lib/python3.6/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/usr/local/lib/python3.6/dist-packages/ipykernel_launcher.py", line 16, in <module>
app.launch_new_instance()
File "/usr/local/lib/python3.6/dist-packages/traitlets/config/application.py", line 664, in launch_instance
app.start()
File "/usr/local/lib/python3.6/dist-packages/ipykernel/kernelapp.py", line 477, in start
ioloop.IOLoop.instance().start()
File "/usr/local/lib/python3.6/dist-packages/tornado/ioloop.py", line 888, in start
handler_func(fd_obj, events)
File "/usr/local/lib/python3.6/dist-packages/tornado/stack_context.py", line 277, in null_wrapper
return fn(*args, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/zmq/eventloop/zmqstream.py", line 450, in _handle_events
self._handle_recv()
File "/usr/local/lib/python3.6/dist-packages/zmq/eventloop/zmqstream.py", line 480, in _handle_recv
self._run_callback(callback, msg)
File "/usr/local/lib/python3.6/dist-packages/zmq/eventloop/zmqstream.py", line 432, in _run_callback
callback(*args, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/tornado/stack_context.py", line 277, in null_wrapper
return fn(*args, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/ipykernel/kernelbase.py", line 283, in dispatcher
return self.dispatch_shell(stream, msg)
File "/usr/local/lib/python3.6/dist-packages/ipykernel/kernelbase.py", line 235, in dispatch_shell
handler(stream, idents, msg)
File "/usr/local/lib/python3.6/dist-packages/ipykernel/kernelbase.py", line 399, in execute_request
user_expressions, allow_stdin)
File "/usr/local/lib/python3.6/dist-packages/ipykernel/ipkernel.py", line 196, in do_execute
res = shell.run_cell(code, store_history=store_history, silent=silent)
File "/usr/local/lib/python3.6/dist-packages/ipykernel/zmqshell.py", line 533, in run_cell
return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/IPython/core/interactiveshell.py", line 2718, in run_cell
interactivity=interactivity, compiler=compiler, result=result)
File "/usr/local/lib/python3.6/dist-packages/IPython/core/interactiveshell.py", line 2822, in run_ast_nodes
if self.run_code(code, result):
File "/usr/local/lib/python3.6/dist-packages/IPython/core/interactiveshell.py", line 2882, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File "<ipython-input-11-90859dc83f76>", line 66, in <module>
main()
File "<ipython-input-11-90859dc83f76>", line 12, in main
model = DAModel()
File "<ipython-input-9-682db36e2a23>", line 148, in __init__
self.logits, self.labels, self.dialogue_lengths)
File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/contrib/crf/python/ops/crf.py", line 257, in crf_log_likelihood
transition_params)
File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/contrib/crf/python/ops/crf.py", line 116, in crf_sequence_score
false_fn=_multi_seq_fn)
File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/layers/utils.py", line 202, in smart_cond
pred, true_fn=true_fn, false_fn=false_fn, name=name)
File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/framework/smart_cond.py", line 59, in smart_cond
name=name)
File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/util/deprecation.py", line 507, in new_func
return func(*args, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/ops/control_flow_ops.py", line 1235, in cond
orig_res_f, res_f = context_f.BuildCondBranch(false_fn)
File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/ops/control_flow_ops.py", line 1061, in BuildCondBranch
original_result = fn()
File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/contrib/crf/python/ops/crf.py", line 104, in _multi_seq_fn
unary_scores = crf_unary_score(tag_indices, sequence_lengths, inputs)
File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/contrib/crf/python/ops/crf.py", line 287, in crf_unary_score
flattened_tag_indices = array_ops.reshape(offsets + tag_indices, [-1])
File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/ops/math_ops.py", line 899, in binary_op_wrapper
return func(x, y, name=name)
File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/ops/math_ops.py", line 1197, in _add_dispatch
return gen_math_ops.add_v2(x, y, name=name)
File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/ops/gen_math_ops.py", line 549, in add_v2
"AddV2", x=x, y=y, name=name)
File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/framework/op_def_library.py", line 794, in _apply_op_helper
op_def=op_def)
File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/util/deprecation.py", line 507, in new_func
return func(*args, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/framework/ops.py", line 3357, in create_op
attrs, op_def, compute_device)
File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/framework/ops.py", line 3426, in _create_op_internal
op_def=op_def)
File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/framework/ops.py", line 1748, in __init__
self._traceback = tf_stack.extract_stack()
Here is the code (which is slightly different from the repo in order to get it to run:
Versions:
Python 3
tensorflow == 1.15.0
pandas == 0.25.3
numpy == 1.17.5
import glob
import pandas as pd
import tensorflow as tf
import pandas as pd
import numpy as np
# preprocess data
file_list = []
for f in glob.glob('swda/*'):
file_list.append(f)
df_list = []
for i in file_list:
df = pd.read_csv(i)
df_list.append(df)
text_list = []
label_list = []
for df in df_list:
df['utterance_no_specialchar_'] = df.utterance_no_specialchar.astype(str)
text = df.utterance_no_specialchar_.tolist()
labels = df.da_category.tolist()
text_list.append(text)
label_list.append(labels)
### new preprocessing step
text_list = [[[j] for j in i] for i in text_list]
tok_data = [y[0] for x in text_list for y in x]
tokenizer = tf.keras.preprocessing.text.Tokenizer()
tokenizer.fit_on_texts(tok_data)
sequences = []
for x in text_list:
tmp = []
for y in x:
tmp.append(tokenizer.texts_to_sequences(y)[0])
sequences.append(tmp)
def _pad_sequences(sequences, pad_tok, max_length):
"""
Args:
sequences: a generator of list or tuple
pad_tok: the char to pad with
Returns:
a list of list where each sublist has same length
"""
sequence_padded, sequence_length = [], []
for seq in sequences:
seq = list(seq)
seq_ = seq[:max_length] + [pad_tok]*max(max_length - len(seq), 0)
sequence_padded += [seq_]
sequence_length += [min(len(seq), max_length)]
return sequence_padded, sequence_length
def pad_sequences(sequences, pad_tok, nlevels=1):
"""
Args:
sequences: a generator of list or tuple
pad_tok: the char to pad with
nlevels: "depth" of padding, for the case where we have characters ids
Returns:
a list of list where each sublist has same length
"""
if nlevels == 1:
max_length = max(map(lambda x : len(x), sequences))
sequence_padded, sequence_length = _pad_sequences(sequences,
pad_tok, max_length)
elif nlevels == 2:
max_length_word = max([max(map(lambda x: len(x), seq))
for seq in sequences])
sequence_padded, sequence_length = [], []
for seq in sequences:
# all words are same length now
sp, sl = _pad_sequences(seq, pad_tok, max_length_word)
sequence_padded += [sp]
sequence_length += [sl]
max_length_sentence = max(map(lambda x : len(x), sequences))
sequence_padded, _ = _pad_sequences(sequence_padded,
[pad_tok]*max_length_word, max_length_sentence)
sequence_length, _ = _pad_sequences(sequence_length, 0,
max_length_sentence)
return sequence_padded, sequence_length
def minibatches(data, labels, batch_size):
data_size = len(data)
start_index = 0
num_batches_per_epoch = int((len(data) + batch_size - 1) / batch_size)
for batch_num in range(num_batches_per_epoch):
start_index = batch_num * batch_size
end_index = min((batch_num + 1) * batch_size, data_size)
yield data[start_index: end_index], labels[start_index: end_index]
def select(parameters, length):
"""Select the last valid time step output as the sentence embedding
:params parameters: [batch, seq_len, hidden_dims]
:params length: [batch]
:Returns : [batch, hidden_dims]
"""
shape = tf.shape(parameters)
idx = tf.range(shape[0])
idx = tf.stack([idx, length - 1], axis = 1)
return tf.gather_nd(parameters, idx)
class DAModel():
def __init__(self):
with tf.variable_scope("placeholder"):
self.dialogue_lengths = tf.placeholder(tf.int32, shape = [None], name = "dialogue_lengths")
self.word_ids = tf.placeholder(tf.int32, shape = [None,None,None], name = "word_ids")
self.utterance_lengths = tf.placeholder(tf.int32, shape = [None, None], name = "utterance_lengths")
self.labels = tf.placeholder(tf.int32, shape = [None, None], name = "labels")
self.clip = tf.placeholder(tf.float32, shape = [], name = 'clip')
######################## EMBEDDINGS ###########################################
with tf.variable_scope("embeddings"):
_word_embeddings = tf.get_variable(
name = "_word_embeddings",
dtype = tf.float32,
shape = [words, word_dim],
initializer = tf.random_uniform_initializer()
)
word_embeddings = tf.nn.embedding_lookup(_word_embeddings,self.word_ids, name="word_embeddings")
self.word_embeddings = tf.nn.dropout(word_embeddings, 0.8)
with tf.variable_scope("utterance_encoder"):
s = tf.shape(self.word_embeddings)
batch_size = s[0] * s[1]
time_step = s[-2]
word_embeddings = tf.reshape(self.word_embeddings, [batch_size, time_step, word_dim])
length = tf.reshape(self.utterance_lengths, [batch_size])
fw = tf.nn.rnn_cell.LSTMCell(hidden_size_lstm_1, forget_bias=0.8, state_is_tuple= True)
bw = tf.nn.rnn_cell.LSTMCell(hidden_size_lstm_1, forget_bias=0.8, state_is_tuple= True)
output, _ = tf.nn.bidirectional_dynamic_rnn(fw, bw, word_embeddings,sequence_length=length, dtype = tf.float32)
output = tf.concat(output, axis = -1) # [batch_size, time_step, dim]
# Select the last valid time step output as the utterance embedding,
# this method is more concise than TensorArray with while_loop
# output = select(output, self.utterance_lengths) # [batch_size, dim]
output = select(output, length) # [batch_size, dim]
# output = tf.reshape(output, s[0], s[1], 2 * hidden_size_lstm_1)
output = tf.reshape(output, [s[0], s[1], 2 * hidden_size_lstm_1])
output = tf.nn.dropout(output, 0.8)
with tf.variable_scope("bi-lstm"):
cell_fw = tf.contrib.rnn.BasicLSTMCell(hidden_size_lstm_2, state_is_tuple = True)
cell_bw = tf.contrib.rnn.BasicLSTMCell(hidden_size_lstm_2, state_is_tuple = True)
(output_fw, output_bw), _ = tf.nn.bidirectional_dynamic_rnn(cell_fw, cell_bw, output, sequence_length = self.dialogue_lengths, dtype = tf.float32)
outputs = tf.concat([output_fw, output_bw], axis = -1)
outputs = tf.nn.dropout(outputs, 0.8)
with tf.variable_scope("proj1"):
output = tf.reshape(outputs, [-1, 2 * hidden_size_lstm_2])
W = tf.get_variable("W", dtype = tf.float32, shape = [2 * hidden_size_lstm_2, proj1], initializer= tf.contrib.layers.xavier_initializer())
b = tf.get_variable("b", dtype = tf.float32, shape = [proj1], initializer=tf.zeros_initializer())
output = tf.nn.relu(tf.matmul(output, W) + b)
with tf.variable_scope("proj2"):
W = tf.get_variable("W", dtype = tf.float32, shape = [proj1, proj2], initializer= tf.contrib.layers.xavier_initializer())
b = tf.get_variable("b", dtype = tf.float32, shape = [proj2], initializer=tf.zeros_initializer())
output = tf.nn.relu(tf.matmul(output, W) + b)
with tf.variable_scope("logits"):
nstep = tf.shape(outputs)[1]
W = tf.get_variable("W", dtype = tf.float32,shape=[proj2, tags], initializer = tf.random_uniform_initializer())
b = tf.get_variable("b", dtype = tf.float32,shape = [tags],initializer=tf.zeros_initializer())
pred = tf.matmul(output, W) + b
self.logits = tf.reshape(pred, [-1, nstep, tags])
with tf.variable_scope("loss"):
log_likelihood, self.trans_params = tf.contrib.crf.crf_log_likelihood(
self.logits, self.labels, self.dialogue_lengths)
self.loss = tf.reduce_mean(-log_likelihood) + tf.nn.l2_loss(W) + tf.nn.l2_loss(b)
#tf.summary.scalar("loss", self.loss)
with tf.variable_scope("viterbi_decode"):
viterbi_sequence, _ = tf.contrib.crf.crf_decode(self.logits, self.trans_params, self.dialogue_lengths)
batch_size = tf.shape(self.dialogue_lengths)[0]
output_ta = tf.TensorArray(dtype = tf.float32, size = 1, dynamic_size = True)
def body(time, output_ta_1):
length = self.dialogue_lengths[time]
vcode = viterbi_sequence[time][:length]
true_labs = self.labels[time][:length]
accurate = tf.reduce_sum(tf.cast(tf.equal(vcode, true_labs), tf.float32))
output_ta_1 = output_ta_1.write(time, accurate)
return time + 1, output_ta_1
def condition(time, output_ta_1):
return time < batch_size
i = 0
[time, output_ta] = tf.while_loop(condition, body, loop_vars = [i, output_ta])
output_ta = output_ta.stack()
accuracy = tf.reduce_sum(output_ta)
self.accuracy = accuracy / tf.reduce_sum(tf.cast(self.dialogue_lengths, tf.float32))
#tf.summary.scalar("accuracy", self.accuracy)
with tf.variable_scope("train_op"):
optimizer = tf.train.AdagradOptimizer(0.1)
#if tf.greater(self.clip , 0):
grads, vs = zip(*optimizer.compute_gradients(self.loss))
grads, gnorm = tf.clip_by_global_norm(grads, self.clip)
self.train_op = optimizer.apply_gradients(zip(grads, vs))
#else:
# self.train_op = optimizer.minimize(self.loss)
#self.merged = tf.summary.merge_all()
### Set model variables
hidden_size_lstm_1 = 200
hidden_size_lstm_2 = 200
tags = 39 # assuming number of classes to predict?
word_dim = 300
proj1 = 200
proj2 = 100
words = 20001
# words = 8759 + 1 # max(num_unique_word_tokens)
batchSize = 2
log_dir = "train"
model_dir = "DAModel"
model_name = "ckpt"
### Run model
def main():
# tokenize and vectorize text data to prepare for embedding
train_data = sequences[:75]
train_labels = label_list[:75]
dev_data = sequences[75:]
dev_labels = label_list[75:]
config = tf.ConfigProto()
config.gpu_options.per_process_gpu_memory_fraction = 0.4
with tf.Session(config = config) as sess:
model = DAModel()
sess.run(tf.global_variables_initializer())
clip = 2
saver = tf.train.Saver()
#writer = tf.summary.FileWriter("D:\\Experimemts\\tensorflow\\DA\\train", sess.graph)
writer = tf.summary.FileWriter("train", sess.graph)
counter = 0
for epoch in range(10):
for dialogues, labels in minibatches(train_data, train_labels, batchSize):
_, dialogue_lengthss = pad_sequences(dialogues, 0)
word_idss, utterance_lengthss = pad_sequences(dialogues, 0, nlevels = 2)
true_labs = labels
labs_t, _ = pad_sequences(true_labs, 0)
counter += 1
train_loss, train_accuracy, _ = sess.run([model.loss, model.accuracy,model.train_op], feed_dict = {model.word_ids: word_idss, model.utterance_lengths: utterance_lengthss, model.dialogue_lengths: dialogue_lengthss, model.labels:labs_t, model.clip :clip} )
#writer.add_summary(summary, global_step = counter)
print("step = {}, train_loss = {}, train_accuracy = {}".format(counter, train_loss, train_accuracy))
train_precision_summ = tf.Summary()
train_precision_summ.value.add(
tag='train_accuracy', simple_value=train_accuracy)
writer.add_summary(train_precision_summ, counter)
train_loss_summ = tf.Summary()
train_loss_summ.value.add(
tag='train_loss', simple_value=train_loss)
writer.add_summary(train_loss_summ, counter)
if counter % 1 == 0:
loss_dev = []
acc_dev = []
for dev_dialogues, dev_labels in minibatches(dev_data, dev_labels, batchSize):
_, dialogue_lengthss = pad_sequences(dev_dialogues, 0)
word_idss, utterance_lengthss = pad_sequences(dev_dialogues, 0, nlevels = 2)
true_labs = dev_labels
labs_t, _ = pad_sequences(true_labs, 0)
dev_loss, dev_accuacy = sess.run([model.loss, model.accuracy], feed_dict = {model.word_ids: word_idss, model.utterance_lengths: utterance_lengthss, model.dialogue_lengths: dialogue_lengthss, model.labels:labs_t})
loss_dev.append(dev_loss)
acc_dev.append(dev_accuacy)
valid_loss = sum(loss_dev) / len(loss_dev)
valid_accuracy = sum(acc_dev) / len(acc_dev)
dev_precision_summ = tf.Summary()
dev_precision_summ.value.add(
tag='dev_accuracy', simple_value=valid_accuracy)
writer.add_summary(dev_precision_summ, counter)
dev_loss_summ = tf.Summary()
dev_loss_summ.value.add(
tag='dev_loss', simple_value=valid_loss)
writer.add_summary(dev_loss_summ, counter)
print("counter = {}, dev_loss = {}, dev_accuacy = {}".format(counter, valid_loss, valid_accuracy))
if __name__ == "__main__":
tf.reset_default_graph()
main()
The data comes from here and looks like this:
[[['what '],
['do you want to start '],
['f uh laughter you hit you hit f uh '],
['it doesnt matter '],
['f um were discussing the capital punishment i believe '],
['right '],
['you are right '],
['yeah '],
[' i i suppose i should have '],
['f uh which '],
['i am am pro capital punishment except that i dont like the way its done '],
['uhhuh '],
['f uh yeah '],
['f uh i f uh i guess i i hate to see anyone die f uh ']
...
]]
The dataset to train the model can be found here:
https://github.com/cmeaton/Hierarchical_BiLSTM-CRF_Encoder/tree/master/swda_parsed
I'm having a hard time understanding what this error even means and how to approach understanding it. Any advice would be much appreciated. Thanks.
Introduction
I think the main problem is a data mismatch in the sizes of the arrays (or matrixes or other structure) you are feeding sess.run. Specifically when you are calling:
train_loss, train_accuracy, _ = sess.run([model.loss, model.accuracy,model.train_op], feed_dict = {model.word_ids: word_idss, model.utterance_lengths: utterance_lengthss, model.dialogue_lengths: dialogue_lengthss, model.labels:labs_t, model.clip :clip} )
And more specifically, this error here hints that it's a mismatch problem:
tensorflow.python.framework.errors_impl.InvalidArgumentError:
indices[317] = [317, -1] does not index into param shape [318,39,400]
[[{{node utterance_encoder/GatherNd}}]]
I considered maybe that running on a fresh install might result in a error-free run.
I am getting similar errors but also a whole list of warnings.
Please note I am running on windows 7 and using python 3.6.1.
Versions
I have tried the following tensorflow versions but with no success:
tf 1.15
tf 1.14
tf 1.13.1
tf 1.12
tf 1.11
tf 1.10
tf 1.10 with downgraded keras to 2.2.1
Steps
Installed python 3.6.1 (supported version of tensorflow). Installed for All Users. Set the Path. Installed in C:\Python36
pip3 install --user --upgrade tensorflow==1.15
pip3 install --user --upgrade pandas == 0.25.3
pip3 install --user --upgrade numpy == 1.17.5
Download the following: https://github.com/cmeaton/Hierarchical_BiLSTM-CRF_Encoder/tree/master/swda_parsed
Run the provided code
Result (Includes Many Warnings)
I think the following might be important:
tensorflow.python.framework.errors_impl.InvalidArgumentError: indices[317] = [317, -1] does not index into param shape [318,39,400]
[[{{node utterance_encoder/GatherNd}}]]
Full Trace
WARNING:tensorflow:From test.py:313: The name tf.reset_default_graph is deprecated. Please use tf.compat.v1.reset_default_graph instead.
WARNING:tensorflow:From test.py:256: The name tf.ConfigProto is deprecated. Please use tf.compat.v1.ConfigProto instead.
WARNING:tensorflow:From test.py:259: The name tf.Session is deprecated. Please use tf.compat.v1.Session instead.
2020-01-31 12:13:10.096283: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2
WARNING:tensorflow:From test.py:119: The name tf.variable_scope is deprecated. Please use tf.compat.v1.variable_scope instead.
WARNING:tensorflow:From test.py:121: The name tf.placeholder is deprecated. Please use tf.compat.v1.placeholder instead.
WARNING:tensorflow:From test.py:130: The name tf.get_variable is deprecated. Please use tf.compat.v1.get_variable instead.
WARNING:tensorflow:From test.py:137: calling dropout (from tensorflow.python.ops.nn_ops) with keep_prob is deprecated and will be removed in a future version.
Instructions for updating:
Please use `rate` instead of `keep_prob`. Rate should be set to `rate = 1 - keep_prob`.
WARNING:tensorflow:From test.py:147: LSTMCell.__init__ (from tensorflow.python.ops.rnn_cell_impl) is deprecated and will be removed in a future version.
Instructions for updating:
This class is equivalent as tf.keras.layers.LSTMCell, and will be replaced by that in Tensorflow 2.0.
WARNING:tensorflow:From test.py:150: bidirectional_dynamic_rnn (from tensorflow.python.ops.rnn) is deprecated and will be removed in a future version.
Instructions for updating:
Please use `keras.layers.Bidirectional(keras.layers.RNN(cell))`, which is equivalent to this API
WARNING:tensorflow:From D:\Users\bakopme\AppData\Roaming\Python\Python36\site-packages\tensorflow_core\python\ops\rnn.py:464: dynamic_rnn (from tensorflow.python.ops.rnn) is deprecated and will be removed in a future version.
Instructions for updating:
Please use `keras.layers.RNN(cell)`, which is equivalent to this API
WARNING:tensorflow:From D:\Users\bakopme\AppData\Roaming\Python\Python36\site-packages\tensorflow_core\python\ops\rnn_cell_impl.py:958: Layer.add_variable (from tensorflow.python.keras.engine.base_layer) is deprecated and will be removed in a future version.
Instructions for updating:
Please use `layer.add_weight` method instead.
WARNING:tensorflow:From D:\Users\bakopme\AppData\Roaming\Python\Python36\site-packages\tensorflow_core\python\ops\rnn_cell_impl.py:962: calling Zeros.__init__ (from tensorflow.python.ops.init_ops) with dtype is deprecated and will be removed in a future version.
Instructions for updating:
Call initializer instance with the dtype argument instead of passing it to the constructor
WARNING:tensorflow:From D:\Users\bakopme\AppData\Roaming\Python\Python36\site-packages\tensorflow_core\python\ops\rnn.py:244: where (from tensorflow.python.ops.array_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.where in 2.0, which has the same broadcast rule as np.where
WARNING:tensorflow:
The TensorFlow contrib module will not be included in TensorFlow 2.0.
For more information, please see:
* https://github.com/tensorflow/community/blob/master/rfcs/20180907-contrib-sunset.md
* https://github.com/tensorflow/addons
* https://github.com/tensorflow/io (for I/O related ops)
If you depend on functionality not listed there, please file an issue.
WARNING:tensorflow:From test.py:163: BasicLSTMCell.__init__ (from tensorflow.python.ops.rnn_cell_impl) is deprecated and will be removed in a future version.
Instructions for updating:
This class is equivalent as tf.keras.layers.LSTMCell, and will be replaced by that in Tensorflow 2.0.
WARNING:tensorflow:From test.py:223: The name tf.train.AdagradOptimizer is deprecated. Please use tf.compat.v1.train.AdagradOptimizer instead.
WARNING:tensorflow:From D:\Users\bakopme\AppData\Roaming\Python\Python36\site-packages\tensorflow_core\python\training\adagrad.py:76: calling Constant.__init__ (from tensorflow.python.ops.init_ops) with dtype is deprecated and will be removed in a future version.
Instructions for updating:
Call initializer instance with the dtype argument instead of passing it to the constructor
WARNING:tensorflow:From test.py:261: The name tf.global_variables_initializer is deprecated. Please use tf.compat.v1.global_variables_initializer instead.
WARNING:tensorflow:From test.py:263: The name tf.train.Saver is deprecated. Please use tf.compat.v1.train.Saver instead.
WARNING:tensorflow:From test.py:265: The name tf.summary.FileWriter is deprecated. Please use tf.compat.v1.summary.FileWriter instead.
2020-01-31 12:13:16.563989: W tensorflow/core/framework/op_kernel.cc:1651] OP_REQUIRES failed at gather_nd_op.cc:47 : Invalid argument: indices[317] = [317, -1] does not index into param shape [318,39,400]
Traceback (most recent call last):
File "D:\Users\bakopme\AppData\Roaming\Python\Python36\site-packages\tensorflow_core\python\client\session.py", line 1365, in _do_call
return fn(*args)
File "D:\Users\bakopme\AppData\Roaming\Python\Python36\site-packages\tensorflow_core\python\client\session.py", line 1350, in _run_fn
target_list, run_metadata)
File "D:\Users\bakopme\AppData\Roaming\Python\Python36\site-packages\tensorflow_core\python\client\session.py", line 1443, in _call_tf_sessionrun
run_metadata)
tensorflow.python.framework.errors_impl.InvalidArgumentError: indices[317] = [317, -1] does not index into param shape [318,39,400]
[[{{node utterance_encoder/GatherNd}}]]
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "test.py", line 314, in <module>
main()
File "test.py", line 274, in main
train_loss, train_accuracy, _ = sess.run([model.loss, model.accuracy,model.train_op], feed_dict = {model.word_ids: word_idss, model.utterance_lengths: utterance_lengthss, model.dialogue_lengths: dialogue_lengthss, model.labels:labs_t, model.clip :clip} )
File "D:\Users\bakopme\AppData\Roaming\Python\Python36\site-packages\tensorflow_core\python\client\session.py", line 956, in run
run_metadata_ptr)
File "D:\Users\bakopme\AppData\Roaming\Python\Python36\site-packages\tensorflow_core\python\client\session.py", line 1180, in _run
feed_dict_tensor, options, run_metadata)
File "D:\Users\bakopme\AppData\Roaming\Python\Python36\site-packages\tensorflow_core\python\client\session.py", line 1359, in _do_run
run_metadata)
File "D:\Users\bakopme\AppData\Roaming\Python\Python36\site-packages\tensorflow_core\python\client\session.py", line 1384, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: indices[317] = [317, -1] does not index into param shape [318,39,400]
[[node utterance_encoder/GatherNd (defined at D:\Users\bakopme\AppData\Roaming\Python\Python36\site-packages\tensorflow_core\python\framework\ops.py:1748) ]]
Original stack trace for 'utterance_encoder/GatherNd':
File "test.py", line 314, in <module>
main()
File "test.py", line 260, in main
model = DAModel()
File "test.py", line 155, in __init__
output = select(output, length) # [batch_size, dim]
File "test.py", line 114, in select
return tf.gather_nd(parameters, idx)
File "D:\Users\bakopme\AppData\Roaming\Python\Python36\site-packages\tensorflow_core\python\util\dispatch.py", line 180, in wrapper
return target(*args, **kwargs)
File "D:\Users\bakopme\AppData\Roaming\Python\Python36\site-packages\tensorflow_core\python\ops\array_ops.py", line 4277, in gather_nd
return gen_array_ops.gather_nd(params, indices, name=name)
File "D:\Users\bakopme\AppData\Roaming\Python\Python36\site-packages\tensorflow_core\python\ops\gen_array_ops.py", line 3975, in gather_nd
"GatherNd", params=params, indices=indices, name=name)
File "D:\Users\bakopme\AppData\Roaming\Python\Python36\site-packages\tensorflow_core\python\framework\op_def_library.py", line 794, in _apply_op_helper
op_def=op_def)
File "D:\Users\bakopme\AppData\Roaming\Python\Python36\site-packages\tensorflow_core\python\util\deprecation.py", line 507, in new_func
return func(*args, **kwargs)
File "D:\Users\bakopme\AppData\Roaming\Python\Python36\site-packages\tensorflow_core\python\framework\ops.py", line 3357, in create_op
attrs, op_def, compute_device)
File "D:\Users\bakopme\AppData\Roaming\Python\Python36\site-packages\tensorflow_core\python\framework\ops.py", line 3426, in _create_op_internal
op_def=op_def)
File "D:\Users\bakopme\AppData\Roaming\Python\Python36\site-packages\tensorflow_core\python\framework\ops.py", line 1748, in __init__
self._traceback = tf_stack.extract_stack()
Let's focus on the error:
Invalid argument: Incompatible shapes: [2,185] vs. [2,229]
The problem seems to be that an operation between two tensors fails, because their shapes are incompatible.
It's possible that the tensorflow version you've selected is less permissive than the one used by the author.
According to this issue, the author guesses he used tensorflow==1.8.
So first I would suggest you try to use this earlier version, or others before\after that (1.7, 1.9, 1.10 etc).
Also, earlier versions may not have the keras package integrated to them as it is today, so you may want to use a specific keras version as well.
For example according to this issue, what helped was to downgrade to keras==2.2.2.
If that doesn't help, maybe one of these will: 1, 2, 3, 4, 5, 6
I have around 550K samples, each sample being 200x50x1. The size of this dataset is around 57GB.
I want to train a network on this set but I am having trouble reading it.
batch_size=8
def _read_py_function(filename,labels_slice):
with h5py.File(filename, 'r') as f:
data_slice = np.asarray(f['feats'])
print(data_slice.shape)
return data_slice, labels_slice
placeholder_files = tf.placeholder(tf.string, [None])
placeholder_labels = tf.placeholder(tf.int32, [None])
dataset = tf.data.Dataset.from_tensor_slices((placeholder_files,placeholder_labels))
dataset = dataset.map(
lambda filename, label: tuple(tf.py_func(
_read_py_function, [filename,label], [tf.uint8, tf.int32])))
dataset = dataset.shuffle(buffer_size=50000)
dataset = dataset.batch(batch_size)
iterator = tf.data.Iterator.from_structure(dataset.output_types, dataset.output_shapes)
data_X, data_y = iterator.get_next()
data_y = tf.cast(data_y, tf.int32)
net = conv_layer(inputs=data_X,num_outputs=8, kernel_size=3, stride=2, scope='rcl_0')
net = pool_layer(inputs=net,kernel_size=2,scope='pl_0')
net = dropout_layer(inputs=net,scope='dl_0')
net = flatten_layer(inputs=net,scope='flatten_0')
net = dense_layer(inputs=net,num_outputs=256,scope='dense_0')
net = dense_layer(inputs=net,num_outputs=64,scope='dense_1')
out = dense_layer(inputs=net,num_outputs=10,scope='dense_2')
And I run the session using :
sess.run(train_iterator, feed_dict = {placeholder_files: filenames, placeholder_labels: ytrain})
try:
while True:
_, loss, acc = sess.run([train_op, loss_op, accuracy_op])
train_loss += loss
train_accuracy += acc
except tf.errors.OutOfRangeError:
pass
But I am getting the error even before running the session :
Traceback (most recent call last):
File "SFCC-trial-134.py", line 297, in <module>
net = rcnn_layer(inputs=data_X,num_outputs=8, kernel_size=3, stride=2, scope='rcl_0')
File "SFCC-trial-134.py", line 123, in rcnn_layer
reuse=False)
File "SFCC-trial-134.py", line 109, in conv_layer
reuse = reuse
File "/home/priyam.jain/tensorflow-gpu-python3/lib/python3.5/site-packages/tensorflow/contrib/framework/python/ops/arg_scope.py", line 183, in func_with_args
return func(*args, **current_args)
File "/home/priyam.jain/tensorflow-gpu-python3/lib/python3.5/site-packages/tensorflow/contrib/layers/python/layers/layers.py", line 1154, in convolution2d
conv_dims=2)
File "/home/priyam.jain/tensorflow-gpu-python3/lib/python3.5/site-packages/tensorflow/contrib/framework/python/ops/arg_scope.py", line 183, in func_with_args
return func(*args, **current_args)
File "/home/priyam.jain/tensorflow-gpu-python3/lib/python3.5/site-packages/tensorflow/contrib/layers/python/layers/layers.py", line 1025, in convolution
(conv_dims + 2, input_rank))
TypeError: %d format: a number is required, not NoneType
I though about using TFRecords but had a hard time creating those. Couldn't find a good post where I learn to create them for my kind of dataset.
conv_layer is defined as follows :
def conv_layer(inputs, num_outputs, kernel_size, stride, normalizer_fn=None, activation_fn=nn.relu, trainable=True, scope='noname', reuse=False):
net = slim.conv2d(inputs = inputs,
num_outputs = num_outputs,
kernel_size = kernel_size,
stride = stride,
normalizer_fn = normalizer_fn,
activation_fn = activation_fn,
trainable = trainable,
scope = scope,
reuse = reuse
)
return net
Do not pass tf.py_func inside your map function. You can read the file image by passing the function name directly inside your map function. I am posing only the relevant parts of the code.
def _read_py_function(filename, label):
return tf.zeros((224, 224, 3), dtype=tf.float32), tf.ones((1,), dtype=tf.int32)
dataset = dataset.map(lambda filename, label: _read_py_function(filename, label))
Another change is your iterator will expect only floating point of input. So you will have to change your tf.uint8 type of output to float.
I try to make a simple LSTM network with 2 layers stacked. To that purpose I use MultiRNNCell. I followed tutorials and other stack topics, but I still have a problem to run my network. Below you can find declaration of initial state I found on stack.
cell_count = 10 # timesteps
num_hidden = 4 # hidden layer num of features
num_classes = 1
num_layers = 2
state_size = 4
init_c = tf.Variable(tf.zeros([batch_size, cell_count]), trainable=False)
init_h = tf.Variable(tf.zeros([batch_size, cell_count]), trainable=False)
initial_state = rnn.LSTMStateTuple(init_c, init_h) #[num_layers, 2, batch_size, state_size])
Below you can find how my model looks like:
def generate_model_graph(self, data):
L1 = self.generate_layer(self.cell_count)
L2 = self.generate_layer(self.cell_count)
#outputs from L1
L1_outs, _ = L1(data, self.initial_state)
#reverse output array
L2_inputs = L1_outs[::-1]
L2_outs, _ = L2(L2_inputs, self.initial_state)
predicted_vals = tf.add(tf.matmul(self.weights["out"], L2_outs), self.biases["out"])
L2_out = tf.nn.sigmoid(predicted_vals)
return L2_out
def generate_layer(self, size):
cells = [rnn.BasicLSTMCell(self.num_hidden) for _ in range(size)]
return rnn.MultiRNNCell(cells)
And run session:
def train_model(self, generator):
tr, cost = self.define_model()
init = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init)
for _ in range(self.n_epochs):
batch_x, batch_y = self._prepare_data(generator)
init_state = tf.zeros((self.cell_count, self.num_hidden))
t, c = sess.run([tr, cost], feed_dict={self.X: batch_x, self.Y:batch_y, self.initial_state:init_state})
print(c)
Unfortunately, I still get an error saying 'Variable' object is not iterable.
File "detector_lstm_v2.py", line 104, in <module>
c.train_model(data_gen)
File "detector_lstm_v2.py", line 38, in train_model
tr, cost = self.define_model()
File "detector_lstm_v2.py", line 51, in define_model
predicted_vals = self.generate_model_graph(self.X)
File "detector_lstm_v2.py", line 65, in generate_model_graph
L1_outs, _ = L1(data, self.initial_state)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/rnn_cell_impl.py", line 232, in __call__
return super(RNNCell, self).__call__(inputs, state)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/layers/base.py", line 329, in __call__
outputs = super(Layer, self).__call__(inputs, *args, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/base_layer.py", line 703, in __call__
outputs = self.call(inputs, *args, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/rnn_cell_impl.py", line 1325, in call
cur_inp, new_state = cell(cur_inp, cur_state)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/rnn_cell_impl.py", line 339, in __call__
*args, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/layers/base.py", line 329, in __call__
outputs = super(Layer, self).__call__(inputs, *args, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/base_layer.py", line 703, in __call__
outputs = self.call(inputs, *args, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/rnn_cell_impl.py", line 633, in call
c, h = state
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/variables.py", line 491, in __iter__
raise TypeError("'Variable' object is not iterable.")
TypeError: 'Variable' object is not iterable.
Does any know how to solve this problem?
You are creating a multi layer rnn cell but you are passing a single state.
Use this to create your state:
initial_state = L1.zero_state()
or use it to initialize the variable if you need a variable.
There are some "naming“ problems in your code that make me think you are misunderstanding something here.
There are different parameters:
The hidden size of your layers: it is the units attribute of the RNNCell constructor. All the states of your cell nees to have a shape [bacth_size, hidden_size] (and not cell count]
Your cell_count in your code is not determining the length of the sequence but "how deep" your network is.
The length of the sequence is automatically determined on the input sequence you are passing to your model (which needs to be a list of tensors).
I recommend you to have a look at the TF tutorial on Recurrent Neural Networks here and maybe this answer here to understand what a RNNCell is w.r.t. RNN literature (it is a layer and not a single cell).
I have implemented the following LSTM class in Tensorflow, where the unroll operation is inspired by the dynamic_rnn() implementation within Tensorflow:
class LSTM():
def __init__(self, dim_x, dim_h, batch_size):
self.batch_size = batch_size
self.dim_x = dim_x
self.dim_h = dim_h
self.W_x_h = normal([dim_x, 4*dim_h])
self.W_h_h = normal([dim_h, 4*dim_h])
self.b_h = zeros([4*dim_h])
self.h_0 = zeros([batch_size, dim_h])
self.c_0 = zeros([batch_size, dim_h])
def lstmStep(self, x_t, h_t_minus, c_t_minus):
lstm_mat = tf.matmul(x_t, self.W_x_h) + tf.matmul(h_t_minus, self.W_h_h) \
+ self.b_h
i_lin, f_lin, o_lin, g_lin = tf.split(1, 4, lstm_mat)
i_t = tf.sigmoid(i_lin); f_t = tf.sigmoid(f_lin)
o_t = tf.sigmoid(o_lin); g_t = tf.tanh(g_lin)
c_t = c_t_minus * f_t + i_t * g_t
h_t = o_t * tf.tanh(c_t)
return h_t, c_t
def lstmUnroll(self, in_batch):
seq_len = array_ops.shape(in_batch)[0]
in_batch_ta = tensor_array_ops.TensorArray(dtype = in_batch.dtype, size = seq_len)
in_batch_ta = in_batch_ta.unpack(in_batch)
h_arr = tensor_array_ops.TensorArray(dtype = in_batch.dtype, size = seq_len)
time = array_ops.constant(0, dtype=tf.int32)
inputs_got_shape = in_batch.get_shape().with_rank(3)
(const_time_steps, const_batch_size, const_depth) = inputs_got_shape.as_list()
def compute(time, h_t, c_t, h_arr_t):
x_t = in_batch_ta.read(time)
h_t, c_t = self.lstmStep(x_t, h_t, c_t)
h_arr_t = h_arr_t.write(time, h_t)
return [time+1, h_t, c_t, h_arr_t]
(_1, _2, _3, h_arr) = control_flow_ops.While(
cond=lambda time, _1, _2, _3: time < seq_len,
body=compute,
loop_vars=(time, self.h_0, self.c_0, h_arr),
parallel_iterations=32)
output = h_arr.pack()
return output
I define a graph using the LSTM with some cost function. The graph compiles properly, and I'm able to forward propagate using 'in_batch' which is of size [sequence_length, batch_size, input_dim]. 'sequence_length' can vary for different batches. However, when I use an optimizer(Adam) with the cost function, I get the following error message:
Traceback (most recent call last):
File "textToImage.py", line 351, in <module>
opt = tf.train.AdamOptimizer().minimize(temp)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/optimizer.py", line 192, in minimize
name=name)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/optimizer.py", line 297, in apply_gradients
update_ops.append(self._apply_dense(grad, var))
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/adam.py", line 129, in _apply_dense
self._epsilon_t, grad, use_locking=self._use_locking).op
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/gen_training_ops.py", line 81, in apply_adam
use_locking=use_locking, name=name)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/op_def_library.py", line 655, in apply_op
op_def=op_def)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 2042, in create_op
set_shapes_for_outputs(ret)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1528, in set_shapes_for_outputs
shapes = shape_func(op)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/training/training_ops.py", line 72, in _ApplyAdamShape
grad_shape = op.inputs[9].get_shape().merge_with(v_shape)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/tensor_shape.py", line 541, in merge_with
self.assert_same_rank(other)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/tensor_shape.py", line 584, in assert_same_rank
"Shapes %s and %s must have the same rank" % (self, other))
ValueError: Shapes () and (1000, 512) must have the same rank
Here 1000 is 'dim_x' and 512 is 4*'dim_h', so the error is for 'W_x_h'. I have tried using '.set_shape()' for 'x_t', 'h_t', 'c_t' and 'output' in 'lstmUnroll()', still fails.
Any ideas to make it work with the optimizer?