无法在 Tensorflow 中输入形状的值

Posted 2023-03-12

【中文标题】无法在 Tensorflow 中输入形状的值

【英文标题】：Cannot feed value of shape in Tensorflow

【发布时间】：2020-09-09 13:23:06

【问题描述】：

我正在尝试使用指定的确切代码按照教程训练 CNN 模型，但收到错误消息。下面是我正在使用的代码。

# Common imports
from __future__ import division, print_function, unicode_literals
import numpy as np
import os
import numpy as np
from sklearn.datasets import load_sample_image

from io import open
import tensorflow.compat.v1 as tf
tf.disable_v2_behavior() 

# to make this notebook's output stable across runs
def reset_graph(seed=42):
    tf.reset_default_graph()
    tf.set_random_seed(seed)
    np.random.seed(seed)

# To plot pretty figures
%matplotlib inline
import matplotlib
import matplotlib.pyplot as plt
plt.rcParams['axes.labelsize'] = 14
plt.rcParams['xtick.labelsize'] = 12
plt.rcParams['ytick.labelsize'] = 12

# Where to save the figures
PROJECT_ROOT_DIR = "."
CHAPTER_ID = "cnn"

def save_fig(fig_id, tight_layout=True):
    path = os.path.join(PROJECT_ROOT_DIR, "images", CHAPTER_ID, fig_id + ".png")
    print("Saving figure", fig_id)
    if tight_layout:
        plt.tight_layout()
    plt.savefig(path, format='png', dpi=300)

#A couple utility functions to plot grayscale and RGB images:
def plot_image(image):
    plt.imshow(image, cmap="gray", interpolation="nearest")
    plt.axis("off")

def plot_color_image(image):
    plt.imshow(image.astype(np.uint8),interpolation="nearest")
    plt.axis("off")

#Convolutional Layer

china = load_sample_image("china.jpg")
flower = load_sample_image("flower.jpg")
image = china[150:220, 130:250]
height, width, channels = image.shape
image_grayscale = image.mean(axis=2).astype(np.float32)
images = image_grayscale.reshape(1, height, width, 1)

fmap = np.zeros(shape=(7, 7, 1, 2), dtype=np.float32)
fmap[:, 3, 0, 0] = 1
fmap[3, :, 0, 1] = 1
plot_image(fmap[:, :, 0, 0])
plt.show()
plot_image(fmap[:, :, 0, 1])
plt.show()

reset_graph()

X = tf.placeholder(tf.float32, shape=(None, height, width, 1))
feature_maps = tf.constant(fmap)
convolution = tf.nn.conv2d(X, feature_maps, strides=[1,1,1,1], padding="SAME")

with tf.Session() as sess:
    output = convolution.eval(feed_dict=X: images)

plot_image(images[0, :, :, 0])
save_fig("china_original", tight_layout=False)
plt.show()

plot_image(output[0, :, :, 0])
save_fig("china_vertical", tight_layout=False)
plt.show()

plot_image(output[0, :, :, 1])
save_fig("china_horizontal", tight_layout=False)
plt.show()


# Simple Example

# Load sample images
china = load_sample_image("china.jpg")
flower = load_sample_image("flower.jpg")
dataset = np.array([china, flower], dtype=np.float32)
batch_size, height, width, channels = dataset.shape

# Create 2 filters
filters = np.zeros(shape=(7, 7, channels, 2), dtype=np.float32)
filters[:, 3, :, 0] = 1  # vertical line
filters[3, :, :, 1] = 1  # horizontal line

# Create a graph with input X plus a convolutional layer applying the 2 filters
X = tf.placeholder(tf.float32, shape=(None, height, width, channels))
convolution = tf.nn.conv2d(X, filters, strides=[1,2,2,1], padding="SAME")

with tf.Session() as sess:
    output = sess.run(convolution, feed_dict=X: dataset)

plt.imshow(output[0, :, :, 1], cmap="gray") # plot 1st image's 2nd feature map
plt.show()

for image_index in (0, 1):
    for feature_map_index in (0, 1):
        plot_image(output[image_index, :, :, feature_map_index])
        plt.show()

reset_graph()

X = tf.placeholder(shape=(None, height, width, channels), dtype=tf.float32)
conv = tf.layers.conv2d(X, filters=2, kernel_size=7, strides=[2,2],
                        padding="SAME")

init = tf.global_variables_initializer()

with tf.Session() as sess:
    init.run()
    output = sess.run(conv, feed_dict=X: dataset)

plt.imshow(output[0, :, :, 1], cmap="gray") # plot 1st image's 2nd feature map
plt.show()


reset_graph()

filter_primes = np.array([2., 3., 5., 7., 11., 13.], dtype=np.float32)
x = tf.constant(np.arange(1, 13+1, dtype=np.float32).reshape([1, 1, 13, 1]))
filters = tf.constant(filter_primes.reshape(1, 6, 1, 1))

valid_conv = tf.nn.conv2d(x, filters, strides=[1, 1, 5, 1], padding='VALID')
same_conv = tf.nn.conv2d(x, filters, strides=[1, 1, 5, 1], padding='SAME')

with tf.Session() as sess:
    print("VALID:\n", valid_conv.eval())
    print("SAME:\n", same_conv.eval())


print("VALID:")
print(np.array([1,2,3,4,5,6]).T.dot(filter_primes))
print(np.array([6,7,8,9,10,11]).T.dot(filter_primes))
print("SAME:")
print(np.array([0,1,2,3,4,5]).T.dot(filter_primes))
print(np.array([5,6,7,8,9,10]).T.dot(filter_primes))
print(np.array([10,11,12,13,0,0]).T.dot(filter_primes))


batch_size, height, width, channels = dataset.shape

filters = np.zeros(shape=(7, 7, channels, 2), dtype=np.float32)
filters[:, 3, :, 0] = 1  # vertical line
filters[3, :, :, 1] = 1  # horizontal line

X = tf.placeholder(tf.float32, shape=(None, height, width, channels))
max_pool = tf.nn.max_pool(X, ksize=[1,2,2,1], strides=[1,2,2,1],padding="VALID")

with tf.Session() as sess:
    output = sess.run(max_pool, feed_dict=X: dataset)

plt.imshow(output[0].astype(np.uint8))  # plot the output for the 1st image
plt.show()


plot_color_image(dataset[0])
save_fig("china_original")
plt.show()

plot_color_image(output[0])
save_fig("china_max_pool")
plt.show()

width = 28
channels = 1
n_inputs = height * width

conv1_fmaps = 32
conv1_ksize = 3
conv1_stride = 1
conv1_pad = "SAME"

conv2_fmaps = 64
conv2_ksize = 3
conv2_stride = 2
conv2_pad = "SAME"

pool3_fmaps = conv2_fmaps

n_fc1 = 64
n_outputs = 10

reset_graph()

with tf.name_scope("inputs"):
    X = tf.placeholder(tf.float32, shape=[None, n_inputs], name="X")
    X_reshaped = tf.reshape(X, shape=[-1, height, width, channels])
    y = tf.placeholder(tf.int32, shape=[None], name="y")

conv1 = tf.layers.conv2d(X_reshaped, filters=conv1_fmaps, kernel_size=conv1_ksize,
                         strides=conv1_stride, padding=conv1_pad,
                         activation=tf.nn.relu, name="conv1")
conv2 = tf.layers.conv2d(conv1, filters=conv2_fmaps, kernel_size=conv2_ksize,
                         strides=conv2_stride, padding=conv2_pad,
                         activation=tf.nn.relu, name="conv2")

with tf.name_scope("pool3"):
    pool3 = tf.nn.max_pool(conv2, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding="VALID")
    pool3_flat = tf.reshape(pool3, shape=[-1, pool3_fmaps * 7 * 7])

with tf.name_scope("fc1"):
    fc1 = tf.layers.dense(pool3_flat, n_fc1, activation=tf.nn.relu, name="fc1")

with tf.name_scope("output"):
    logits = tf.layers.dense(fc1, n_outputs, name="output")
    Y_proba = tf.nn.softmax(logits, name="Y_proba")

with tf.name_scope("train"):
    xentropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=logits, labels=y)
    loss = tf.reduce_mean(xentropy)
    optimizer = tf.train.AdamOptimizer()
    training_op = optimizer.minimize(loss)

with tf.name_scope("eval"):
    correct = tf.nn.in_top_k(logits, y, 1)
    accuracy = tf.reduce_mean(tf.cast(correct, tf.float32))

with tf.name_scope("init_and_save"):
    init = tf.global_variables_initializer()
    saver = tf.train.Saver()


(X_train, y_train), (X_test, y_test) = tf.keras.datasets.mnist.load_data()
X_train = X_train.astype(np.float32).reshape(-1, 28*28) / 255.0
X_test = X_test.astype(np.float32).reshape(-1, 28*28) / 255.0
y_train = y_train.astype(np.int32)
y_test = y_test.astype(np.int32)
X_valid, X_train = X_train[:5000], X_train[5000:]
y_valid, y_train = y_train[:5000], y_train[5000:]

def shuffle_batch(X, y, batch_size):
    rnd_idx = np.random.permutation(len(X))
    n_batches = len(X) // batch_size
    for batch_idx in np.array_split(rnd_idx, n_batches):
        X_batch, y_batch = X[batch_idx], y[batch_idx]
        yield X_batch, y_batch

n_epochs = 10
batch_size = 100

with tf.Session() as sess:
    init.run()
    for epoch in range(n_epochs):
        for X_batch, y_batch in shuffle_batch(X_train, y_train, batch_size):
            sess.run(training_op, feed_dict=X: X_batch, y: y_batch)
        acc_batch = accuracy.eval(feed_dict=X: X_batch, y: y_batch)
        acc_test = accuracy.eval(feed_dict=X: X_test, y: y_test)
        print(epoch, "Last batch accuracy:", acc_batch, "Test accuracy:", acc_test)

        save_path = saver.save(sess, "./my_mnist_model")

一切运行良好，直到最后一节（使用 tf.Session() 作为 sess:) 我收到以下错误：

ValueError: Cannot feed value of shape (100, 784) for Tensor 'inputs/X:0', which has shape '(?, 1960)'

我一直在阅读Stack Overflow上的以下相关主题，其中大部分似乎没有解决方案。

ValueError: Cannot feed value of shape (784,) for Tensor 'x:0', which has shape '(?, 784)'

ValueError: Cannot feed value of shape

Sketch_RNN , ValueError: Cannot feed value of shape

编辑：我包含了一些我认为是用于单独模块的代码，但正在定义我的一些参数，即高度。

【问题讨论】：

错误很明显，你试图给x一个形状不兼容的值。您没有在脚本中显示height 的值，它似乎已设置为70，而不是预期的28。

所以 height 参数是在代码前面定义的，我将其排除并编辑了我的帖子以现在显示。似乎我们将高度硬编码为与一张图像（china.jpg）相同，我是否需要将所有图像的大小调整为与初始高度设置相同的大小才能起作用？

您可以选择在神经网络中或在将它们作为输入传递之前缩放图像，但您必须确保输入的值与预期的输入大小相匹配。

【参考方案1】：

谢谢jdehesa，我可以简单地为高度输入一个静态参数，程序似乎运行成功。

height=28