I am trying to convert Tensorflow's official basic word2vec implementation to use tf.Estimator.
The issue is that the loss function( sampled_softmax_loss
or nce_loss
) gives an error when using Tensorflow Estimators. It works perfectly fine in the original implementation.
Here's is Tensorflow's official basic word2vec implementation:
https://github.com/tensorflow/tensorflow/blob/master/tensorflow/examples/tutorials/word2vec/word2vec_basic.py
Here is the Google Colab notebook where I implemented this code, which is working.
https://colab.research.google.com/drive/1nTX77dRBHmXx6PEF5pmYpkIVxj_TqT5I
Here is the Google Colab notebook where I altered the code so that it uses Tensorflow Estimator, which is Not working.
https://colab.research.google.com/drive/1IVDqGwMx6BK5-Bgrw190jqHU6tt3ZR3e
For convenience, here is exact code from the Estimator version above where I define model_fn
batch_size = 128
embedding_size = 128 # Dimension of the embedding vector.
skip_window = 1 # How many words to consider left and right.
num_skips = 2 # How many times to reuse an input to generate a label.
num_sampled = 64 # Number of negative examples to sample.
def my_model( features, labels, mode, params):
with tf.name_scope('inputs'):
train_inputs = features
train_labels = labels
with tf.name_scope('embeddings'):
embeddings = tf.Variable(
tf.random_uniform([vocabulary_size, embedding_size], -1.0, 1.0))
embed = tf.nn.embedding_lookup(embeddings, train_inputs)
with tf.name_scope('weights'):
nce_weights = tf.Variable(
tf.truncated_normal(
[vocabulary_size, embedding_size],
stddev=1.0 / math.sqrt(embedding_size)))
with tf.name_scope('biases'):
nce_biases = tf.Variable(tf.zeros([vocabulary_size]))
with tf.name_scope('loss'):
loss = tf.reduce_mean(
tf.nn.nce_loss(
weights=nce_weights,
biases=nce_biases,
labels=train_labels,
inputs=embed,
num_sampled=num_sampled,
num_classes=vocabulary_size))
tf.summary.scalar('loss', loss)
if mode == "train":
with tf.name_scope('optimizer'):
optimizer = tf.train.GradientDescentOptimizer(1.0).minimize(loss)
return tf.estimator.EstimatorSpec(mode, loss=loss, train_op=optimizer)
And here is where I call the estimator and training
word2vecEstimator = tf.estimator.Estimator(
model_fn=my_model,
params={
'batch_size': 16,
'embedding_size': 10,
'num_inputs': 3,
'num_sampled': 128,
'batch_size': 16
})
word2vecEstimator.train(
input_fn=generate_batch,
steps=10)
And this the error message I get when I call the Estimator training:
INFO:tensorflow:Calling model_fn.
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-22-955f44867ee5> in <module>()
1 word2vecEstimator.train(
2 input_fn=generate_batch,
----> 3 steps=10)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/estimator/estimator.py in train(self, input_fn, hooks, steps, max_steps, saving_listeners)
352
353 saving_listeners = _check_listeners_type(saving_listeners)
--> 354 loss = self._train_model(input_fn, hooks, saving_listeners)
355 logging.info('Loss for final step: %s.', loss)
356 return self
/usr/local/lib/python3.6/dist-packages/tensorflow/python/estimator/estimator.py in _train_model(self, input_fn, hooks, saving_listeners)
1205 return self._train_model_distributed(input_fn, hooks, saving_listeners)
1206 else:
-> 1207 return self._train_model_default(input_fn, hooks, saving_listeners)
1208
1209 def _train_model_default(self, input_fn, hooks, saving_listeners):
/usr/local/lib/python3.6/dist-packages/tensorflow/python/estimator/estimator.py in _train_model_default(self, input_fn, hooks, saving_listeners)
1235 worker_hooks.extend(input_hooks)
1236 estimator_spec = self._call_model_fn(
-> 1237 features, labels, model_fn_lib.ModeKeys.TRAIN, self.config)
1238 global_step_tensor = training_util.get_global_step(g)
1239 return self._train_with_estimator_spec(estimator_spec, worker_hooks,
/usr/local/lib/python3.6/dist-packages/tensorflow/python/estimator/estimator.py in _call_model_fn(self, features, labels, mode, config)
1193
1194 logging.info('Calling model_fn.')
-> 1195 model_fn_results = self._model_fn(features=features, **kwargs)
1196 logging.info('Done calling model_fn.')
1197
<ipython-input-20-9d389437162a> in my_model(features, labels, mode, params)
33 inputs=embed,
34 num_sampled=num_sampled,
---> 35 num_classes=vocabulary_size))
36
37 # Add the loss value as a scalar to summary.
/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/nn_impl.py in nce_loss(weights, biases, labels, inputs, num_sampled, num_classes, num_true, sampled_values, remove_accidental_hits, partition_strategy, name)
1246 remove_accidental_hits=remove_accidental_hits,
1247 partition_strategy=partition_strategy,
-> 1248 name=name)
1249 sampled_losses = sigmoid_cross_entropy_with_logits(
1250 labels=labels, logits=logits, name="sampled_losses")
/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/nn_impl.py in _compute_sampled_logits(weights, biases, labels, inputs, num_sampled, num_classes, num_true, sampled_values, subtract_log_q, remove_accidental_hits, partition_strategy, name, seed)
1029 with ops.name_scope(name, "compute_sampled_logits",
1030 weights + [biases, inputs, labels]):
-> 1031 if labels.dtype != dtypes.int64:
1032 labels = math_ops.cast(labels, dtypes.int64)
1033 labels_flat = array_ops.reshape(labels, [-1])
TypeError: data type not understood
Edit: Upon request, here's what a typical output for input_fn looks like
print(generate_batch(batch_size=8, num_skips=2, skip_window=1))
(array([3081, 3081, 12, 12, 6, 6, 195, 195], dtype=int32), array([[5234],
[ 12],
[ 6],
[3081],
[ 12],
[ 195],
[ 6],
[ 2]], dtype=int32))
You use generate_batch
like a variable here:
word2vecEstimator.train(
input_fn=generate_batch,
steps=10)
Call the function with generate_batch()
.
But I think you must pass some values to the function.
It might be that tensors and ops must be in the input_fn
, not in the 'model_fn'
I found this issue #4026 which solved my problem ... Maybe it is just me being stupid, but it would be great if you mention that the tensors and ops all have to be inside the input_fn somewhere in the documentation.
You have to call read_batch_examples from somewhere inside input_fn so that the tensors it creates are in the graph that Estimator creates in fit().
https://github.com/tensorflow/tensorflow/issues/8042
Oh I feel like an idiot! I've been creating the op outside of the graph scope. It works now, can't believe I didn't think to try that. Thanks a lot! This is a non-issue and has been resolved
https://github.com/tensorflow/tensorflow/issues/4026
However, there still is not enough info on what's causing the issue. This is just a lead.
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With