This repository has been archived by the owner on Sep 11, 2020. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 40
ValueError: Variable topic_embedding already exists, disallowed. Did you mean to set reuse=True or reuse=tf.AUTO_REUSE in VarScope? Originally defined at: #40
Labels
bug
Something isn't working
Comments
Does the twenty newsgroups example work when you set I'm assuming you pulled since my commit last night? |
Yes, I did a pull this morning.
Here’s my results from twenty_newsgroups:
import pandas as pd
from lda2vec.nlppipe import Preprocessor
# Data directory
data_dir ="data"
# Where to save preprocessed data
clean_data_dir = "data/clean_data_twenty_newsgroups"
# Name of input file. Should be inside of data_dir
input_file = "20_newsgroups.txt"
# Should we load pretrained embeddings from file
load_embeds = True
# Read in data file
df = pd.read_csv(data_dir+"/"+input_file, sep="\t")
# Initialize a preprocessor
P = Preprocessor(df, "texts", max_features=30000, maxlen=10000, min_count=30, nlp="en_core_web_lg")
# Run the preprocessing on your dataframe
P.preprocess()
# Load embeddings from file if we choose to do so
if load_embeds:
# Load embedding matrix from file path - change path to where you saved them
embedding_matrix = P.load_glove("glove.6B.300d.txt")
else:
embedding_matrix = None
# Save data to data_dir
P.save_data(clean_data_dir, embedding_matrix=embedding_matrix)
from lda2vec import utils, model
# Path to preprocessed data
data_path = "data/clean_data_twenty_newsgroups"
# Whether or not to load saved embeddings file
load_embeds = True
# Load data from files
(idx_to_word, word_to_idx, freqs, pivot_ids,
target_ids, doc_ids, embed_matrix) = utils.load_preprocessed_data(data_path, load_embed_matrix=load_embeds)
# Number of unique documents
num_docs = doc_ids.max() + 1
# Number of unique words in vocabulary (int)
vocab_size = len(freqs)
# Embed layer dimension size
# If not loading embeds, change 128 to whatever size you want.
embed_size = embed_matrix.shape[1] if load_embeds else 128
# Number of topics to cluster into
num_topics = 20
# Amount of iterations over entire dataset
num_epochs = 200
# Batch size - Increase/decrease depending on memory usage
batch_size = 500
# Epoch that we want to "switch on" LDA loss
switch_loss_epoch = 0
# Pretrained embeddings value
pretrained_embeddings = embed_matrix if load_embeds else None
# If True, save logdir, otherwise don't
save_graph = True
# Initialize the model
m = model(num_docs,
vocab_size,
num_topics,
embedding_size=embed_size,
pretrained_embeddings=pretrained_embeddings,
freqs=freqs,
batch_size = batch_size,
save_graph_def=save_graph)
# Train the model
m.train(pivot_ids,
target_ids,
doc_ids,
len(pivot_ids),
num_epochs,
idx_to_word=idx_to_word,
switch_loss_epoch=switch_loss_epoch)
# Visualize topics with pyldavis
utils.generate_ldavis_data(data_path, m, idx_to_word, freqs, vocab_size)
…--------------------------------------------------------------------------
InvalidArgumentError Traceback (most recent call last)
~/anaconda/envs/ai/lib/python3.6/site-packages/tensorflow/python/client/session.py in _do_call(self, fn, *args)
1333 try:
-> 1334 return fn(*args)
1335 except errors.OpError as e:
~/anaconda/envs/ai/lib/python3.6/site-packages/tensorflow/python/client/session.py in _run_fn(feed_dict, fetch_list, target_list, options, run_metadata)
1318 return self._call_tf_sessionrun(
-> 1319 options, feed_dict, fetch_list, target_list, run_metadata)
1320
~/anaconda/envs/ai/lib/python3.6/site-packages/tensorflow/python/client/session.py in _call_tf_sessionrun(self, options, feed_dict, fetch_list, target_list, run_metadata)
1406 self._session, options, feed_dict, fetch_list, target_list,
-> 1407 run_metadata)
1408
InvalidArgumentError: indices[0] = 5451 is not in [0, 5451)
[[{{node nce_loss/negative_sampling/nce_loss/embedding_lookup}} = GatherV2[Taxis=DT_INT32, Tindices=DT_INT64, Tparams=DT_FLOAT, _class=["loc:@Optimizer/train/update_nce_weights/AssignSub"], _device="/job:localhost/replica:0/task:0/device:CPU:0"](nce_weights/read, nce_loss/negative_sampling/nce_loss/concat, nce_loss/negative_sampling/nce_loss/embedding_lookup/axis)]]
During handling of the above exception, another exception occurred:
InvalidArgumentError Traceback (most recent call last)
<ipython-input-3-50c29a55db24> in <module>()
48 num_epochs,
49 idx_to_word=idx_to_word,
---> 50 switch_loss_epoch=switch_loss_epoch)
51
52 # Visualize topics with pyldavis
~/Lda2vec-Tensorflow/lda2vec/Lda2vec.py in train(self, pivot_words, target_words, doc_ids, data_size, num_epochs, switch_loss_epoch, save_every, report_every, print_topics_every, idx_to_word)
244
245 # Run a step of the model
--> 246 summary, _, l, lw2v, llda, step = self.sesh.run(fetches, feed_dict=feed_dict)
247
248 # Prints log every "report_every" epoch
~/anaconda/envs/ai/lib/python3.6/site-packages/tensorflow/python/client/session.py in run(self, fetches, feed_dict, options, run_metadata)
927 try:
928 result = self._run(None, fetches, feed_dict, options_ptr,
--> 929 run_metadata_ptr)
930 if run_metadata:
931 proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)
~/anaconda/envs/ai/lib/python3.6/site-packages/tensorflow/python/client/session.py in _run(self, handle, fetches, feed_dict, options, run_metadata)
1150 if final_fetches or final_targets or (handle and feed_dict_tensor):
1151 results = self._do_run(handle, final_targets, final_fetches,
-> 1152 feed_dict_tensor, options, run_metadata)
1153 else:
1154 results = []
~/anaconda/envs/ai/lib/python3.6/site-packages/tensorflow/python/client/session.py in _do_run(self, handle, target_list, fetch_list, feed_dict, options, run_metadata)
1326 if handle is None:
1327 return self._do_call(_run_fn, feeds, fetches, targets, options,
-> 1328 run_metadata)
1329 else:
1330 return self._do_call(_prun_fn, handle, feeds, fetches)
~/anaconda/envs/ai/lib/python3.6/site-packages/tensorflow/python/client/session.py in _do_call(self, fn, *args)
1346 pass
1347 message = error_interpolation.interpolate(message, self._graph)
-> 1348 raise type(e)(node_def, op, message)
1349
1350 def _extend_graph(self):
InvalidArgumentError: indices[0] = 5451 is not in [0, 5451)
[[node nce_loss/negative_sampling/nce_loss/embedding_lookup (defined at /home/ubuntu/Lda2vec-Tensorflow/lda2vec/word_embedding.py:46) = GatherV2[Taxis=DT_INT32, Tindices=DT_INT64, Tparams=DT_FLOAT, _class=["loc:@Optimizer/train/update_nce_weights/AssignSub"], _device="/job:localhost/replica:0/task:0/device:CPU:0"](nce_weights/read, nce_loss/negative_sampling/nce_loss/concat, nce_loss/negative_sampling/nce_loss/embedding_lookup/axis)]]
Caused by op 'nce_loss/negative_sampling/nce_loss/embedding_lookup', defined at:
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/runpy.py", line 193, in _run_module_as_main
"__main__", mod_spec)
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/ipykernel_launcher.py", line 16, in <module>
app.launch_new_instance()
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/traitlets/config/application.py", line 658, in launch_instance
app.start()
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/ipykernel/kernelapp.py", line 486, in start
self.io_loop.start()
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/tornado/platform/asyncio.py", line 127, in start
self.asyncio_loop.run_forever()
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/asyncio/base_events.py", line 427, in run_forever
self._run_once()
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/asyncio/base_events.py", line 1440, in _run_once
handle._run()
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/asyncio/events.py", line 145, in _run
self._callback(*self._args)
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/tornado/ioloop.py", line 759, in _run_callback
ret = callback()
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/tornado/stack_context.py", line 276, in null_wrapper
return fn(*args, **kwargs)
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/zmq/eventloop/zmqstream.py", line 536, in <lambda>
self.io_loop.add_callback(lambda : self._handle_events(self.socket, 0))
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/zmq/eventloop/zmqstream.py", line 450, in _handle_events
self._handle_recv()
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/zmq/eventloop/zmqstream.py", line 480, in _handle_recv
self._run_callback(callback, msg)
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/zmq/eventloop/zmqstream.py", line 432, in _run_callback
callback(*args, **kwargs)
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/tornado/stack_context.py", line 276, in null_wrapper
return fn(*args, **kwargs)
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/ipykernel/kernelbase.py", line 283, in dispatcher
return self.dispatch_shell(stream, msg)
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/ipykernel/kernelbase.py", line 233, in dispatch_shell
handler(stream, idents, msg)
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/ipykernel/kernelbase.py", line 399, in execute_request
user_expressions, allow_stdin)
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/ipykernel/ipkernel.py", line 208, in do_execute
res = shell.run_cell(code, store_history=store_history, silent=silent)
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/ipykernel/zmqshell.py", line 537, in run_cell
return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2662, in run_cell
raw_cell, store_history, silent, shell_futures)
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2785, in _run_cell
interactivity=interactivity, compiler=compiler, result=result)
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2903, in run_ast_nodes
if self.run_code(code, result):
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2963, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File "<ipython-input-3-50c29a55db24>", line 41, in <module>
save_graph_def=save_graph)
File "/home/ubuntu/Lda2vec-Tensorflow/lda2vec/Lda2vec.py", line 82, in __init__
handles = self._build_graph()
File "/home/ubuntu/Lda2vec-Tensorflow/lda2vec/Lda2vec.py", line 162, in _build_graph
loss_word2vec = self.w_embed(context, y)
File "/home/ubuntu/Lda2vec-Tensorflow/lda2vec/word_embedding.py", line 46, in __call__
sampled_values=sampler))
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/tensorflow/python/ops/nn_impl.py", line 1248, in nce_loss
name=name)
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/tensorflow/python/ops/nn_impl.py", line 1062, in _compute_sampled_logits
weights, all_ids, partition_strategy=partition_strategy)
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/tensorflow/python/ops/embedding_ops.py", line 313, in embedding_lookup
transform_fn=None)
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/tensorflow/python/ops/embedding_ops.py", line 133, in _embedding_lookup_and_transform
result = _clip(array_ops.gather(params[0], ids, name=name),
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/tensorflow/python/ops/array_ops.py", line 2675, in gather
return gen_array_ops.gather_v2(params, indices, axis, name=name)
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/tensorflow/python/ops/gen_array_ops.py", line 3332, in gather_v2
"GatherV2", params=params, indices=indices, axis=axis, name=name)
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 488, in new_func
return func(*args, **kwargs)
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3274, in create_op
op_def=op_def)
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1770, in __init__
self._traceback = tf_stack.extract_stack()
InvalidArgumentError (see above for traceback): indices[0] = 5451 is not in [0, 5451)
[[node nce_loss/negative_sampling/nce_loss/embedding_lookup (defined at /home/ubuntu/Lda2vec-Tensorflow/lda2vec/word_embedding.py:46) = GatherV2[Taxis=DT_INT32, Tindices=DT_INT64, Tparams=DT_FLOAT, _class=["loc:@Optimizer/train/update_nce_weights/AssignSub"], _device="/job:localhost/replica:0/task:0/device:CPU:0"](nce_weights/read, nce_loss/negative_sampling/nce_loss/concat, nce_loss/negative_sampling/nce_loss/embedding_lookup/axis)]]
On Mar 25, 2019, at 10:11 AM, Nathan Raw ***@***.***> wrote:
Does the twenty newsgroups example work when you set pretrained_embeddings=False right now? There weren't any errors for me yesterday.
I'm assuming you pulled since my commit last night?
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub <#40 (comment)>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AC9i28KC1DGj7rrzurEfExTCheXcnbErks5vaQNMgaJpZM4cHWDr>.
|
tensorflow.__version__
'1.12.0'
… On Mar 25, 2019, at 10:30 AM, David Laxer ***@***.***> wrote:
Yes, I did a pull this morning.
Here’s my results from twenty_newsgroups:
import pandas as pd
from lda2vec.nlppipe import Preprocessor
# Data directory
data_dir ="data"
# Where to save preprocessed data
clean_data_dir = "data/clean_data_twenty_newsgroups"
# Name of input file. Should be inside of data_dir
input_file = "20_newsgroups.txt"
# Should we load pretrained embeddings from file
load_embeds = True
# Read in data file
df = pd.read_csv(data_dir+"/"+input_file, sep="\t")
# Initialize a preprocessor
P = Preprocessor(df, "texts", max_features=30000, maxlen=10000, min_count=30, nlp="en_core_web_lg")
# Run the preprocessing on your dataframe
P.preprocess()
# Load embeddings from file if we choose to do so
if load_embeds:
# Load embedding matrix from file path - change path to where you saved them
embedding_matrix = P.load_glove("glove.6B.300d.txt")
else:
embedding_matrix = None
# Save data to data_dir
P.save_data(clean_data_dir, embedding_matrix=embedding_matrix)
from lda2vec import utils, model
# Path to preprocessed data
data_path = "data/clean_data_twenty_newsgroups"
# Whether or not to load saved embeddings file
load_embeds = True
# Load data from files
(idx_to_word, word_to_idx, freqs, pivot_ids,
target_ids, doc_ids, embed_matrix) = utils.load_preprocessed_data(data_path, load_embed_matrix=load_embeds)
# Number of unique documents
num_docs = doc_ids.max() + 1
# Number of unique words in vocabulary (int)
vocab_size = len(freqs)
# Embed layer dimension size
# If not loading embeds, change 128 to whatever size you want.
embed_size = embed_matrix.shape[1] if load_embeds else 128
# Number of topics to cluster into
num_topics = 20
# Amount of iterations over entire dataset
num_epochs = 200
# Batch size - Increase/decrease depending on memory usage
batch_size = 500
# Epoch that we want to "switch on" LDA loss
switch_loss_epoch = 0
# Pretrained embeddings value
pretrained_embeddings = embed_matrix if load_embeds else None
# If True, save logdir, otherwise don't
save_graph = True
# Initialize the model
m = model(num_docs,
vocab_size,
num_topics,
embedding_size=embed_size,
pretrained_embeddings=pretrained_embeddings,
freqs=freqs,
batch_size = batch_size,
save_graph_def=save_graph)
# Train the model
m.train(pivot_ids,
target_ids,
doc_ids,
len(pivot_ids),
num_epochs,
idx_to_word=idx_to_word,
switch_loss_epoch=switch_loss_epoch)
# Visualize topics with pyldavis
utils.generate_ldavis_data(data_path, m, idx_to_word, freqs, vocab_size)
--------------------------------------------------------------------------
InvalidArgumentError Traceback (most recent call last)
~/anaconda/envs/ai/lib/python3.6/site-packages/tensorflow/python/client/session.py in _do_call(self, fn, *args)
1333 try:
-> 1334 return fn(*args)
1335 except errors.OpError as e:
~/anaconda/envs/ai/lib/python3.6/site-packages/tensorflow/python/client/session.py in _run_fn(feed_dict, fetch_list, target_list, options, run_metadata)
1318 return self._call_tf_sessionrun(
-> 1319 options, feed_dict, fetch_list, target_list, run_metadata)
1320
~/anaconda/envs/ai/lib/python3.6/site-packages/tensorflow/python/client/session.py in _call_tf_sessionrun(self, options, feed_dict, fetch_list, target_list, run_metadata)
1406 self._session, options, feed_dict, fetch_list, target_list,
-> 1407 run_metadata)
1408
InvalidArgumentError: indices[0] = 5451 is not in [0, 5451)
[[{{node nce_loss/negative_sampling/nce_loss/embedding_lookup}} = GatherV2[Taxis=DT_INT32, Tindices=DT_INT64, Tparams=DT_FLOAT, ***@***.***/train/update_nce_weights/AssignSub"], _device="/job:localhost/replica:0/task:0/device:CPU:0"](nce_weights/read, nce_loss/negative_sampling/nce_loss/concat, nce_loss/negative_sampling/nce_loss/embedding_lookup/axis)]]
During handling of the above exception, another exception occurred:
InvalidArgumentError Traceback (most recent call last)
<ipython-input-3-50c29a55db24> in <module>()
48 num_epochs,
49 idx_to_word=idx_to_word,
---> 50 switch_loss_epoch=switch_loss_epoch)
51
52 # Visualize topics with pyldavis
~/Lda2vec-Tensorflow/lda2vec/Lda2vec.py in train(self, pivot_words, target_words, doc_ids, data_size, num_epochs, switch_loss_epoch, save_every, report_every, print_topics_every, idx_to_word)
244
245 # Run a step of the model
--> 246 summary, _, l, lw2v, llda, step = self.sesh.run(fetches, feed_dict=feed_dict)
247
248 # Prints log every "report_every" epoch
~/anaconda/envs/ai/lib/python3.6/site-packages/tensorflow/python/client/session.py in run(self, fetches, feed_dict, options, run_metadata)
927 try:
928 result = self._run(None, fetches, feed_dict, options_ptr,
--> 929 run_metadata_ptr)
930 if run_metadata:
931 proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)
~/anaconda/envs/ai/lib/python3.6/site-packages/tensorflow/python/client/session.py in _run(self, handle, fetches, feed_dict, options, run_metadata)
1150 if final_fetches or final_targets or (handle and feed_dict_tensor):
1151 results = self._do_run(handle, final_targets, final_fetches,
-> 1152 feed_dict_tensor, options, run_metadata)
1153 else:
1154 results = []
~/anaconda/envs/ai/lib/python3.6/site-packages/tensorflow/python/client/session.py in _do_run(self, handle, target_list, fetch_list, feed_dict, options, run_metadata)
1326 if handle is None:
1327 return self._do_call(_run_fn, feeds, fetches, targets, options,
-> 1328 run_metadata)
1329 else:
1330 return self._do_call(_prun_fn, handle, feeds, fetches)
~/anaconda/envs/ai/lib/python3.6/site-packages/tensorflow/python/client/session.py in _do_call(self, fn, *args)
1346 pass
1347 message = error_interpolation.interpolate(message, self._graph)
-> 1348 raise type(e)(node_def, op, message)
1349
1350 def _extend_graph(self):
InvalidArgumentError: indices[0] = 5451 is not in [0, 5451)
[[node nce_loss/negative_sampling/nce_loss/embedding_lookup (defined at /home/ubuntu/Lda2vec-Tensorflow/lda2vec/word_embedding.py:46) = GatherV2[Taxis=DT_INT32, Tindices=DT_INT64, Tparams=DT_FLOAT, ***@***.***/train/update_nce_weights/AssignSub"], _device="/job:localhost/replica:0/task:0/device:CPU:0"](nce_weights/read, nce_loss/negative_sampling/nce_loss/concat, nce_loss/negative_sampling/nce_loss/embedding_lookup/axis)]]
Caused by op 'nce_loss/negative_sampling/nce_loss/embedding_lookup', defined at:
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/runpy.py", line 193, in _run_module_as_main
"__main__", mod_spec)
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/ipykernel_launcher.py", line 16, in <module>
app.launch_new_instance()
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/traitlets/config/application.py", line 658, in launch_instance
app.start()
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/ipykernel/kernelapp.py", line 486, in start
self.io <http://self.io/>_loop.start()
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/tornado/platform/asyncio.py", line 127, in start
self.asyncio_loop.run_forever()
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/asyncio/base_events.py", line 427, in run_forever
self._run_once()
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/asyncio/base_events.py", line 1440, in _run_once
handle._run()
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/asyncio/events.py", line 145, in _run
self._callback(*self._args)
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/tornado/ioloop.py", line 759, in _run_callback
ret = callback()
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/tornado/stack_context.py", line 276, in null_wrapper
return fn(*args, **kwargs)
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/zmq/eventloop/zmqstream.py", line 536, in <lambda>
self.io <http://self.io/>_loop.add_callback(lambda : self._handle_events(self.socket, 0))
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/zmq/eventloop/zmqstream.py", line 450, in _handle_events
self._handle_recv()
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/zmq/eventloop/zmqstream.py", line 480, in _handle_recv
self._run_callback(callback, msg)
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/zmq/eventloop/zmqstream.py", line 432, in _run_callback
callback(*args, **kwargs)
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/tornado/stack_context.py", line 276, in null_wrapper
return fn(*args, **kwargs)
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/ipykernel/kernelbase.py", line 283, in dispatcher
return self.dispatch_shell(stream, msg)
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/ipykernel/kernelbase.py", line 233, in dispatch_shell
handler(stream, idents, msg)
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/ipykernel/kernelbase.py", line 399, in execute_request
user_expressions, allow_stdin)
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/ipykernel/ipkernel.py", line 208, in do_execute
res = shell.run_cell(code, store_history=store_history, silent=silent)
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/ipykernel/zmqshell.py", line 537, in run_cell
return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2662, in run_cell
raw_cell, store_history, silent, shell_futures)
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2785, in _run_cell
interactivity=interactivity, compiler=compiler, result=result)
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2903, in run_ast_nodes
if self.run_code(code, result):
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/IPython/core/interactiveshell.py", line 2963, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File "<ipython-input-3-50c29a55db24>", line 41, in <module>
save_graph_def=save_graph)
File "/home/ubuntu/Lda2vec-Tensorflow/lda2vec/Lda2vec.py", line 82, in __init__
handles = self._build_graph()
File "/home/ubuntu/Lda2vec-Tensorflow/lda2vec/Lda2vec.py", line 162, in _build_graph
loss_word2vec = self.w_embed(context, y)
File "/home/ubuntu/Lda2vec-Tensorflow/lda2vec/word_embedding.py", line 46, in __call__
sampled_values=sampler))
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/tensorflow/python/ops/nn_impl.py", line 1248, in nce_loss
name=name)
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/tensorflow/python/ops/nn_impl.py", line 1062, in _compute_sampled_logits
weights, all_ids, partition_strategy=partition_strategy)
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/tensorflow/python/ops/embedding_ops.py", line 313, in embedding_lookup
transform_fn=None)
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/tensorflow/python/ops/embedding_ops.py", line 133, in _embedding_lookup_and_transform
result = _clip(array_ops.gather(params[0], ids, name=name),
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/tensorflow/python/ops/array_ops.py", line 2675, in gather
return gen_array_ops.gather_v2(params, indices, axis, name=name)
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/tensorflow/python/ops/gen_array_ops.py", line 3332, in gather_v2
"GatherV2", params=params, indices=indices, axis=axis, name=name)
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 488, in new_func
return func(*args, **kwargs)
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3274, in create_op
op_def=op_def)
File "/home/ubuntu/anaconda/envs/ai/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1770, in __init__
self._traceback = tf_stack.extract_stack()
InvalidArgumentError (see above for traceback): indices[0] = 5451 is not in [0, 5451)
[[node nce_loss/negative_sampling/nce_loss/embedding_lookup (defined at /home/ubuntu/Lda2vec-Tensorflow/lda2vec/word_embedding.py:46) = GatherV2[Taxis=DT_INT32, Tindices=DT_INT64, Tparams=DT_FLOAT, ***@***.***/train/update_nce_weights/AssignSub"], _device="/job:localhost/replica:0/task:0/device:CPU:0"](nce_weights/read, nce_loss/negative_sampling/nce_loss/concat, nce_loss/negative_sampling/nce_loss/embedding_lookup/axis)]]
> On Mar 25, 2019, at 10:11 AM, Nathan Raw ***@***.*** ***@***.***>> wrote:
>
> Does the twenty newsgroups example work when you set pretrained_embeddings=False right now? There weren't any errors for me yesterday.
>
> I'm assuming you pulled since my commit last night?
>
> —
> You are receiving this because you authored the thread.
> Reply to this email directly, view it on GitHub <#40 (comment)>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AC9i28KC1DGj7rrzurEfExTCheXcnbErks5vaQNMgaJpZM4cHWDr>.
>
|
For my own sanity, recommenting for you so I can format with markdown. Can't reformat email replies import pandas as pd
from lda2vec.nlppipe import Preprocessor
# Data directory
data_dir ="data"
# Where to save preprocessed data
clean_data_dir = "data/clean_data_twenty_newsgroups"
# Name of input file. Should be inside of data_dir
input_file = "20_newsgroups.txt"
# Should we load pretrained embeddings from file
load_embeds = True
# Read in data file
df = pd.read_csv(data_dir+"/"+input_file, sep="\t")
# Initialize a preprocessor
P = Preprocessor(df, "texts", max_features=30000, maxlen=10000, min_count=30, nlp="en_core_web_lg")
# Run the preprocessing on your dataframe
P.preprocess()
# Load embeddings from file if we choose to do so
if load_embeds:
# Load embedding matrix from file path - change path to where you saved them
embedding_matrix = P.load_glove("glove.6B.300d.txt")
else:
embedding_matrix = None
# Save data to data_dir
P.save_data(clean_data_dir, embedding_matrix=embedding_matrix)
from lda2vec import utils, model
# Path to preprocessed data
data_path = "data/clean_data_twenty_newsgroups"
# Whether or not to load saved embeddings file
load_embeds = True
# Load data from files
(idx_to_word, word_to_idx, freqs, pivot_ids,
target_ids, doc_ids, embed_matrix) = utils.load_preprocessed_data(data_path, load_embed_matrix=load_embeds)
# Number of unique documents
num_docs = doc_ids.max() + 1
# Number of unique words in vocabulary (int)
vocab_size = len(freqs)
# Embed layer dimension size
# If not loading embeds, change 128 to whatever size you want.
embed_size = embed_matrix.shape[1] if load_embeds else 128
# Number of topics to cluster into
num_topics = 20
# Amount of iterations over entire dataset
num_epochs = 200
# Batch size - Increase/decrease depending on memory usage
batch_size = 500
# Epoch that we want to "switch on" LDA loss
switch_loss_epoch = 0
# Pretrained embeddings value
pretrained_embeddings = embed_matrix if load_embeds else None
# If True, save logdir, otherwise don't
save_graph = True
# Initialize the model
m = model(num_docs,
vocab_size,
num_topics,
embedding_size=embed_size,
pretrained_embeddings=pretrained_embeddings,
freqs=freqs,
batch_size = batch_size,
save_graph_def=save_graph)
# Train the model
m.train(pivot_ids,
target_ids,
doc_ids,
len(pivot_ids),
num_epochs,
idx_to_word=idx_to_word,
switch_loss_epoch=switch_loss_epoch)
# Visualize topics with pyldavis
utils.generate_ldavis_data(data_path, m, idx_to_word, freqs, vocab_size) |
Sorry! I’ll paste directly into github.
… On Mar 25, 2019, at 10:55 AM, Nathan Raw ***@***.***> wrote:
For my own sanity, recommenting for you so I can format with markdown. Can't reformat email replies
import pandas as pd
from lda2vec.nlppipe import Preprocessor
# Data directory
data_dir ="data"
# Where to save preprocessed data
clean_data_dir = "data/clean_data_twenty_newsgroups"
# Name of input file. Should be inside of data_dir
input_file = "20_newsgroups.txt"
# Should we load pretrained embeddings from file
load_embeds = True
# Read in data file
df = pd.read_csv(data_dir+"/"+input_file, sep="\t")
# Initialize a preprocessor
P = Preprocessor(df, "texts", max_features=30000, maxlen=10000, min_count=30, nlp="en_core_web_lg")
# Run the preprocessing on your dataframe
P.preprocess()
# Load embeddings from file if we choose to do so
if load_embeds:
# Load embedding matrix from file path - change path to where you saved them
embedding_matrix = P.load_glove("glove.6B.300d.txt")
else:
embedding_matrix = None
# Save data to data_dir
P.save_data(clean_data_dir, embedding_matrix=embedding_matrix)
from lda2vec import utils, model
# Path to preprocessed data
data_path = "data/clean_data_twenty_newsgroups"
# Whether or not to load saved embeddings file
load_embeds = True
# Load data from files
(idx_to_word, word_to_idx, freqs, pivot_ids,
target_ids, doc_ids, embed_matrix) = utils.load_preprocessed_data(data_path, load_embed_matrix=load_embeds)
# Number of unique documents
num_docs = doc_ids.max() + 1
# Number of unique words in vocabulary (int)
vocab_size = len(freqs)
# Embed layer dimension size
# If not loading embeds, change 128 to whatever size you want.
embed_size = embed_matrix.shape[1] if load_embeds else 128
# Number of topics to cluster into
num_topics = 20
# Amount of iterations over entire dataset
num_epochs = 200
# Batch size - Increase/decrease depending on memory usage
batch_size = 500
# Epoch that we want to "switch on" LDA loss
switch_loss_epoch = 0
# Pretrained embeddings value
pretrained_embeddings = embed_matrix if load_embeds else None
# If True, save logdir, otherwise don't
save_graph = True
# Initialize the model
m = model(num_docs,
vocab_size,
num_topics,
embedding_size=embed_size,
pretrained_embeddings=pretrained_embeddings,
freqs=freqs,
batch_size = batch_size,
save_graph_def=save_graph)
# Train the model
m.train(pivot_ids,
target_ids,
doc_ids,
len(pivot_ids),
num_epochs,
idx_to_word=idx_to_word,
switch_loss_epoch=switch_loss_epoch)
# Visualize topics with pyldavis
utils.generate_ldavis_data(data_path, m, idx_to_word, freqs, vocab_size)
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub <#40 (comment)>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AC9i2zr5UL7LjL89uB_bAkFs9tcnV2Ibks5vaQ2QgaJpZM4cHWDr>.
|
No worries 😄 |
At work right now so I can't really help. Just adding this to my todo list tonight. Will get back to you. Sorry that this stuff is always breaking 🙁 . Sooo many improvements lately but they came with many more bugs. |
Also, just to be clear, this is all supposed to be run on Tensorflow 1.5.0. |
Was running into the same error just now. The TF Version was the problem, with 1.5.0 it's working! |
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
I get this error when pretrained_embeddings=None
The text was updated successfully, but these errors were encountered: