使用估计器 (from_generator) 训练 Tensorflow 模型 [英] Train Tensorflow model with estimator (from_generator)

问题描述

我正在尝试用生成器训练一个估算器，但我想为每个迭代提供一个包含样本包的估算器.我显示代码:

I am trying train an estimator with a generator, but I want to feed this estimator with a package of samples for each iteration. I show the code:

def _generator():
for i in range(100):
    feats  = np.random.rand(4,2)
    labels = np.random.rand(4,1)

    yield feats, labels


def input_func_gen():
    shapes = ((4,2),(4,1))
    dataset = tf.data.Dataset.from_generator(generator=_generator,
                                         output_types=(tf.float32, tf.float32),
                                         output_shapes=shapes)
dataset = dataset.batch(4)
# dataset = dataset.repeat(20)
iterator = dataset.make_one_shot_iterator()
features_tensors, labels = iterator.get_next()
features = {'x': features_tensors}
return features, labels


x_col = tf.feature_column.numeric_column(key='x', shape=(4,2))
es = tf.estimator.LinearRegressor(feature_columns=[x_col],model_dir=tf_data)
es = es.train(input_fn=input_func_gen,steps = None)

当我运行此代码时，它会引发此错误:

When I run this code, it raises this error:

    raise ValueError(err.message)
ValueError: Dimensions must be equal, but are 2 and 3 for 'linear/head/labels/assert_equal/Equal' (op: 'Equal') with input shapes: [2], [3].

我该如何调用这个结构??

How do I have to call to this structure??

谢谢！！！

推荐答案

批量大小由 Tensorflow 自动计算并添加到张量形状中，因此不必手动完成.您的生成器还应定义为输出单个样本.

The batch size is automatically computed and added to the tensors shapes by Tensorflow, so it doesn't have to be done manually. Your generator should also be defined to output single samples.

假设形状的位置 0 中的 4 用于批量大小，则:

Assuming the 4 in position 0 of your shapes are for the batch size, then:

import tensorflow as tf
import numpy

def _generator():
    for i in range(100):
        feats  = numpy.random.rand(2)
        labels = numpy.random.rand(1)

        yield feats, labels


def input_func_gen():
    shapes = ((2),(1))
    dataset = tf.data.Dataset.from_generator(generator=_generator,
                                         output_types=(tf.float32, tf.float32),
                                         output_shapes=shapes)
    dataset = dataset.batch(4)
    # dataset = dataset.repeat(20)
    iterator = dataset.make_one_shot_iterator()
    features_tensors, labels = iterator.get_next()
    features = {'x': features_tensors}
    return features, labels


x_col = tf.feature_column.numeric_column(key='x', shape=(2))
es = tf.estimator.LinearRegressor(feature_columns=[x_col])
es = es.train(input_fn=input_func_gen,steps = None)

这篇关于使用估计器 (from_generator) 训练 Tensorflow 模型的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！