[英]No gradients provided in tensorflow (mean_squared_error)
我正在尝试建立一个简单的2个输入神经元(+1个偏差)的网络,将其转换为1个输出神经元来教它“和”功能。 它基于mnist-clissification的示例,因此对于该任务而言可能过于复杂,但是对我而言,这是关于此类蚊帐的一般结构,因此请不要说“您可以用numpy做到”。关于Tensorflow神经网络 所以这是代码:
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()
我对您的代码做了一些小的修改,使他们能够学习and
功能:
1)将您的train_data
更改为float32表示形式。
train_data = np.asarray(np.reshape([[0,0],[0,1],[1,0],[1,1]],[4,2]), dtype=np.float32)`
2)从输出层删除relu激活-一般来说,不建议在输出层中使用relus。 这可能导致死角,并且所有梯度将等于零,这反过来将使任何学习成为可能。
output_layer = tf.layers.dense(inputs=input_layer, units=1, activation=None, name="output_layer")
3)确保在eval_metrics_ops
中将结果取整,以便可以实际测量准确性:
eval_metrics_ops = {"accuracy": tf.metrics.accuracy(labels=labels, predictions=tf.round(output_layer))}
4)不要忘记将您定义的eval_metrics_ops
参数添加到估算器中:
return tf.estimator.EstimatorSpec(mode=mode, predictions=output_layer, loss=loss, eval_metric_ops=eval_metrics_ops)
另外,要记录最后一层的输出,您应该使用:
tensors_to_log = {"The output:": "output_layer/BiasAdd:0"}
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.