python - 将 TensorFlow Graph 转换为使用 Estimator,使用 `sampled_softmax_loss` 或 `nce_loss` 在损失函数中获取“TypeError:数据类型不理解”
问题描述
我正在尝试将 Tensorflow 的官方基本 word2vec 实现转换为使用 tf.Estimator。问题是损失函数(sampled_softmax_loss
或nce_loss
)在使用 TensorFlow 估计器时会出错。它在原始实现中运行良好。
这是 Tensorflow 的官方基本 word2vec 实现:
这是我实现此代码的 Google Colab 笔记本,它正在运行。
https://colab.research.google.com/drive/1nTX77dRBHmXx6PEF5pmYpkIVxj_TqT5I
这是 Google Colab 笔记本,我在其中更改了代码,使其使用无法正常工作的 Tensorflow Estimator。
https://colab.research.google.com/drive/1IVDqGwMx6BK5-Bgrw190jqHU6tt3ZR3e
为方便起见,这是我在上面定义的 Estimator 版本中的确切代码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)
这就是我称之为估算器和训练的地方
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)
这是我在调用 Estimator 培训时收到的错误消息:
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
编辑:根据要求,这是 input_fn 的典型输出的样子
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))
解决方案
你generate_batch
在这里像一个变量一样使用:
word2vecEstimator.train(
input_fn=generate_batch,
steps=10)
用 调用函数generate_batch()
。但我认为你必须将一些值传递给函数。
推荐阅读
- jenkins - 如何从 Jenkins Pipeline 中的嵌套节点获取当前节点的名称?
- grpc - 使用 protobuf-net.Grpc 的客户端回调
- javascript - Cheerio js 无法选择锚标签
- python - cv2.imread 返回 NoneType 而 matplotlib.pyplot 可以读取
- karate - 我刚刚克隆了一个官方空手道项目,并收到一条关于缺少“空手道解析器”的错误消息,我缺少哪个包?
- excel - 如何使用 VBA 从文本框中传输文本
- c# - TableLayoutPanel 未显示所有数据
- actionscript-3 - as3 - 通过不同的位置移动对象
- amazon-web-services - 我是否需要安装 Hadoop 才能在本地运行 Flink 应用程序
- c# - 如何根据所选的 Visual Studio 主题创建自定义 VSIX 向导