当前，tf.nn.sampled_softmax_loss不允许使用float16。
How to run define Tensorflow graph were all variables are in float16 instead instead of float32
我在看
tf.contrib.nn.sampled_sparse_softmax_loss
来自
https://www.tensorflow.org/api_docs/python/tf/contrib/nn/sampled_sparse_softmax_loss
似乎这可能允许float16值。此功能的代码在这里
https://github.com/tensorflow/tensorflow/blob/r1.11/tensorflow/contrib/nn/python/ops/sampling_ops.py
似乎使用了tf.nn.sparse_softmax_cross_entropy_with_logits
似乎支持float16
logits：形状为[d_0，d_1，...，d_ {r-1}，num_classes]和dtype float16，float32或float64的未缩放日志概率。
https://www.tensorflow.org/api_docs/python/tf/nn/sparse_softmax_cross_entropy_with_logits
但是，当我尝试使用它时，出现错误
我的代码
import math
import numpy as np
import tensorflow as tf
vocabulary_size = 10
batch_size = 64
embedding_size = 100
num_inputs =4
num_sampled = 128
graph = tf.Graph()
with graph.as_default(): #took out " , tf.device('/cpu:0')"
train_dataset = tf.placeholder(tf.int32, shape=[batch_size, num_inputs ])
train_labels = tf.placeholder(tf.int32, shape=[batch_size, 1])
embeddings = tf.get_variable( 'embeddings', dtype=tf.float16,
initializer= tf.random_uniform([vocabulary_size, embedding_size], -1.0, 1.0, dtype=tf.float16) )
softmax_weights = tf.get_variable( 'softmax_weights', dtype=tf.float16,
initializer= tf.truncated_normal([vocabulary_size, embedding_size],
stddev=1.0 / math.sqrt(embedding_size), dtype=tf.float16 ) )
softmax_biases = tf.get_variable('softmax_biases', dtype=tf.float16,
initializer= tf.zeros([vocabulary_size], dtype=tf.float16), trainable=False )
embed = tf.nn.embedding_lookup(embeddings, train_dataset) #train data set is
embed_reshaped = tf.reshape( embed, [batch_size*num_inputs, embedding_size] )
segments= np.arange(batch_size).repeat(num_inputs)
averaged_embeds = tf.segment_mean(embed_reshaped, segments, name=None)
sam_sof_los = tf.contrib.nn.sampled_sparse_softmax_loss(weights=softmax_weights, biases=softmax_biases, inputs=averaged_embeds,
labels=train_labels, num_sampled=num_sampled, num_classes=vocabulary_size)
loss = tf.reduce_mean( sam_sof_los )
optimizer = tf.train.AdagradOptimizer(1.0).minimize(loss)
saver = tf.train.Saver()
我的错误消息
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/op_def_library.py in _apply_op_helper(self, op_type_name, name, **keywords)
509 as_ref=input_arg.is_ref,
--> 510 preferred_dtype=default_dtype)
511 except TypeError as err:
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/ops.py in internal_convert_to_tensor(value, dtype, name, as_ref, preferred_dtype, ctx)
1143 if ret is None:
-> 1144 ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
1145
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/ops.py in _TensorTensorConversionFunction(t, dtype, name, as_ref)
980 "Tensor conversion requested dtype %s for Tensor with dtype %s: %r" %
--> 981 (dtype.name, t.dtype.name, str(t)))
982 return t
ValueError: Tensor conversion requested dtype float16 for Tensor with dtype float32: 'Tensor("sampled_sparse_softmax_loss/Log:0", shape=(64, 1), dtype=float32)'
During handling of the above exception, another exception occurred:
TypeError Traceback (most recent call last)
<ipython-input-11-b68afd94e9bd> in <module>()
41
42 sam_sof_los = tf.contrib.nn.sampled_sparse_softmax_loss(weights=softmax_weights , biases=softmax_biases , inputs=averaged_embeds,
---> 43 labels=train_labels, num_sampled=num_sampled, num_classes=vocabulary_size)
44
45
/usr/local/lib/python3.6/dist-packages/tensorflow/contrib/nn/python/ops/sampling_ops.py in sampled_sparse_softmax_loss(weights, biases, labels, inputs, num_sampled, num_classes, sampled_values, remove_accidental_hits, partition_strategy, name)
331 remove_accidental_hits=remove_accidental_hits,
332 partition_strategy=partition_strategy,
--> 333 name=name)
334
335 # There is only one true label. _compute_sampled_logits puts the true logit
/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)
1126 if subtract_log_q:
1127 # Subtract log of Q(l), prior probability that l appears in sampled.
-> 1128 true_logits -= math_ops.log(true_expected_count)
1129 sampled_logits -= math_ops.log(sampled_expected_count)
1130
/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/math_ops.py in binary_op_wrapper(x, y)
860 with ops.name_scope(None, op_name, [x, y]) as name:
861 if isinstance(x, ops.Tensor) and isinstance(y, ops.Tensor):
--> 862 return func(x, y, name=name)
863 elif not isinstance(y, sparse_tensor.SparseTensor):
864 try:
/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/gen_math_ops.py in sub(x, y, name)
8316 if _ctx is None or not _ctx._eager_context.is_eager:
8317 _, _, _op = _op_def_lib._apply_op_helper(
-> 8318 "Sub", x=x, y=y, name=name)
8319 _result = _op.outputs[:]
8320 _inputs_flat = _op.inputs
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/op_def_library.py in _apply_op_helper(self, op_type_name, name, **keywords)
544 "%s type %s of argument '%s'." %
545 (prefix, dtypes.as_dtype(attrs[input_arg.type_attr]).name,
--> 546 inferred_from[input_arg.type_attr]))
547
548 types = [values.dtype]
TypeError: Input 'y' of 'Sub' Op has type float32 that does not match type float16 of argument 'x'.