ValueError：无法为具有形状“（？，637，1162）”的张量u'Placeholder：0'提供形状（637、1162）的值

Question

我收到提到的错误。我想加载单个图像作为输入 并在给定的蒙版图像上训练它以进行图像二进制 分类。

import tensorflow as tf

import os

import cv2

import matplotlib.pyplot as plt

import numpy as np



images = []

file_names = [os.path.join('../', f)
                      for f in os.listdir('../')
                      if f.endswith(".jpg")]

for f in file_names:
            images.append(cv2.cvtColor(cv2.imread(f,1), cv2.COLOR_BGR2GRAY))

img_mask = images[0];

retval,mask_img = cv2.threshold(img_mask, 50, 255, cv2.THRESH_BINARY)

mask_img = mask_img/255

maskk = np.concatenate(mask_img)

x = tf.placeholder(dtype = tf.float32, shape = [None, 637, 1162])

y = tf.placeholder(dtype = tf.int32, shape = [None])

展平输入数据

images_flat = tf.contrib.layers.flatten(x)

全连接层

logits = tf.contrib.layers.fully_connected(images_flat, 2, tf.nn.relu)

定义损失函数

loss = tf.reduce_mean(tf.nn.sparse_softmax_cross_entropy_with_logits(labels = y, logits = logits))

定义优化器

train_op = tf.train.AdamOptimizer(learning_rate=0.001).minimize(loss)

将 logits 转换为标签索引

correct_pred = tf.argmax(logits, 1)

定义准确度指标

accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32)


tf.set_random_seed(1234)
sess = tf.Session()

sess.run(tf.global_variables_initializer())

for i in range(201):

        print('EPOCH', i)
        _, accuracy_val = sess.run([train_op, accuracy], feed_dict={x: 
        images[1], y: maskk})
        if i % 10 == 0:
            print("Loss: ", loss)
        print('DONE WITH EPOCH')

Answer 1

听起来您缺少批量大小维度，请尝试np.expand_dims(image, dim=0)