ValueError: Failed to convert a NumPy array to a Tensor(不支持的

Question

由于ValueError: Failed to convert a NumPy array to a Tensor (Unsupported object type generator).错误，我的代码出现了一些问题。

import matplotlib.pyplot as plt
import tensorflow as tf
import tensorflow_datasets as tfds
from tensorflow import keras
builder = tfds.builder('horses_or_humans')
ds_train = tfds.load(name = 'horses_or_humans', split = 'train')
ds_test = tfds.load(name = 'horses_or_humans', split = 'test')
train_images = np.array([example['image'].numpy()[:,:,0] for example in ds_train])
train_labels = np.array(example['label'].numpy() for example in ds_train)
test_images = np.array([example['image'].numpy()[:,:,0] for example in ds_test])
test_labels = np.array(example['label'].numpy() for example in ds_test)
train_images = train_images.reshape(1027, 300, 300, 1)
test_images = test_images.reshape(256, 300, 300, 1)

我听说这里可能会出现问题。

train_images = train_images.astype('float32')
test_images = test_images.astype('float32')
train_images /= 255
test_images /= 255
model = keras.Sequential([
keras.layers.Flatten(),
keras.layers.Dense(512, activation = 'relu'),
keras.layers.Dense(256, activation = 'relu'),
keras.layers.Dense(2, activation = 'softmax')
])
model.compile(
optimizer = 'adam',
loss = keras.losses.SparseCategoricalCrossentropy(),
metrics = ['accuracy']
)
model.fit(train_images, train_labels, epochs = 5, batch_size = 32)

我已经试过了

train_images = np.array(train_images).astype("float32")
test_images = np.array(test_images).astype("float32")

但遗憾的是它不适合我，所以我将感谢任何帮助。

Answer 1

1. 您应该阅读如何通过tfds加载数据集。当你可以使用本机tensorflow操作时，不应该在tensorflow处理管道中使用NumPy。
你的神经网络架构不适合这个问题。有一些卷积网络的例子。

对于代码，可以这样修改:

ds_train = tfds.load(name='horses_or_humans', split='train', as_supervised=True)
ds_test = tfds.load(name='horses_or_humans', split='test', as_supervised=True)
def normalize_img(image, label):
"""Normalizes images: `uint8` -> `float32`."""
return tf.cast(image, tf.float32) / 255., label
ds_train = ds_train.map(normalize_img)
ds_train = ds_train.cache()
ds_train = ds_train.batch(32)
ds_train = ds_train.prefetch(tf.data.experimental.AUTOTUNE)
model.fit(ds_train, epochs=6)