我正试图建立一个2输入神经元(+1 bias)的简单网络,进入1个输出神经元以教它“和”功能。它是基于mnist-clissification的例子,所以对于任务来说它可能过于复杂,但是关于这种网络的一般结构对我来说,所以请不要说“你可以用numpy来做”或者什么的,它是关于张量流NNs对我来说。因此,这里是代码:在张量流中没有提供梯度(mean_squared_error)
import tensorflow as tf
import numpy as np
tf.logging.set_verbosity(tf.logging.INFO)
def model_fn(features, labels, mode):
input_layer = tf.reshape(features["x"], [-1, 2])
output_layer = tf.layers.dense(inputs=input_layer, units=1, activation=tf.nn.relu, name="output_layer")
if mode == tf.estimator.ModeKeys.PREDICT:
return tf.estimator.EstimatorSpec(mode=mode, predictions=output_layer)
loss = tf.losses.mean_squared_error(labels=labels, predictions=output_layer)
if mode == tf.estimator.ModeKeys.TRAIN:
optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.001)
train_op = optimizer.minimize(loss=loss, global_step=tf.train.get_global_step())
return tf.estimator.EstimatorSpec(mode=mode, loss=loss, train_op=train_op)
eval_metrics_ops = {"accuracy": tf.metrics.accuracy(labels=labels, predictions=output_layer)}
return tf.estimator.EstimatorSpec(mode=mode, predictions=output_layer, loss=loss)
def main(unused_arg):
train_data = np.asarray(np.reshape([[0,0],[0,1],[1,0],[1,1]],[4,2]))
train_labels = np.asarray(np.reshape([0,0,0,1],[4,1]))
eval_data = train_data
eval_labels = train_labels
classifier = tf.estimator.Estimator(model_fn=model_fn, model_dir="/tmp/NN_AND")
tensors_to_log = {"The output:": "output_layer"}
logging_hook = tf.train.LoggingTensorHook(tensors=tensors_to_log,every_n_iter=10)
train_input_fn = tf.estimator.inputs.numpy_input_fn(x={"x":train_data}, y=train_labels, batch_size=10, num_epochs=None, shuffle=True)
classifier.train(input_fn=train_input_fn, steps=2000, hooks=[logging_hook])
eval_input_fn = tf.estimator.inputs.numpy_input_fn(x={"x":eval_data}, y=eval_labels, batch_size=1, shuffle=False)
eval_results = classifier.evaluate(input_fn=eval_input_fn)
print(eval_results)
if __name__ == "__main__":
tf.app.run()
确切的问题是什么? “没有渐变”是什么意思?梯度== 0? – amirbar