2
import tensorflow as tf
import numpy as np
import os
import re
import PIL


def read_image_label_list(img_directory, folder_name):
    # Input:
    #   -Name of folder (test\\\\train)
    # Output:
    #   -List of names of files in folder
    #   -Label associated with each file

    cat_label = 1
    dog_label = 0
    filenames = []
    labels = []

    dir_list = os.listdir(os.path.join(img_directory, folder_name))  # List of all image names in 'folder_name' folder

    # Loop through all images in directory
    for i, d in enumerate(dir_list):
        if re.search("train", folder_name):
            if re.search("cat", d):  # If image filename contains 'Cat', then true
                labels.append(cat_label)
            else:
                labels.append(dog_label)
        filenames.append(os.path.join(img_dir, folder_name, d))

    return filenames, labels


# Define convolutional layer
def conv_layer(input, channels_in, channels_out):
    w_1 = tf.get_variable("weight_conv", [5,5, channels_in, channels_out], initializer=tf.contrib.layers.xavier_initializer())
    b_1 = tf.get_variable("bias_conv", [channels_out], initializer=tf.zeros_initializer())
    conv = tf.nn.conv2d(input, w_1, strides=[1,1,1,1], padding="SAME")
    activation = tf.nn.relu(conv + b_1)
    return activation


# Define fully connected layer
def fc_layer(input, channels_in, channels_out):
    w_2 = tf.get_variable("weight_fc", [channels_in, channels_out], initializer=tf.contrib.layers.xavier_initializer())
    b_2 = tf.get_variable("bias_fc", [channels_out], initializer=tf.zeros_initializer())
    activation = tf.nn.relu(tf.matmul(input, w_2) + b_2)
    return activation


# Define parse function to make input data to decode image into
def _parse_function(img_path, label):
    img_file = tf.read_file(img_path)
    img_decoded = tf.image.decode_image(img_file, channels=3)
    img_decoded.set_shape([None,None,3])
    img_decoded = tf.image.resize_images(img_decoded, (28, 28), method=tf.image.ResizeMethod.NEAREST_NEIGHBOR)
    img_decoded = tf.image.per_image_standardization(img_decoded)
    img_decoded = tf.cast(img_decoded, dty=tf.float32)
    label = tf.one_hot(label, 1)
    return img_decoded, label


tf.reset_default_graph()

# Define parameterspe
EPOCHS = 10
BATCH_SIZE_training = 64
learning_rate = 0.001
img_dir = 'C:/Users/tharu/PycharmProjects/cat_vs_dog/data'
batch_size = 128

# Define data
features, labels = read_image_label_list(img_dir, "train")

# Define dataset
dataset = tf.data.Dataset.from_tensor_slices((features, labels))  # Takes slices in 0th dimension
dataset = dataset.map(_parse_function)
dataset = dataset.batch(batch_size)
iterator = dataset.make_initializable_iterator()

# Get next batch of data from iterator
x, y = iterator.get_next()

# Create the network (use different variable scopes for reuse of variables)
with tf.variable_scope("conv1"):
    conv_1 = conv_layer(x, 3, 32)
    pool_1 = tf.nn.max_pool(conv_1, ksize=[1,2,2,1], strides=[1,2,2,1], padding="SAME")

with tf.variable_scope("conv2"):
    conv_2 = conv_layer(pool_1, 32, 64)
    pool_2 = tf.nn.max_pool(conv_2, ksize=[1,2,2,1], strides=[1,2,2,1], padding="SAME")
    flattened = tf.contrib.layers.flatten(pool_2)

with tf.variable_scope("fc1"):
    fc_1 = fc_layer(flattened, 7*7*64, 1024)
with tf.variable_scope("fc2"):
    logits = fc_layer(fc_1, 1024, 1)


# Define loss function
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=logits, labels=tf.cast(y, dtype=tf.int32)))

# Define optimizer
train = tf.train.AdamOptimizer(learning_rate).minimize(loss)


with tf.Session() as sess:
    # Initiliaze all the variables
    sess.run(tf.global_variables_initializer())

    # Train the network
    for i in range(EPOCHS):
        # Initialize iterator so that it starts at beginning of training set for each epoch
        sess.run(iterator.initializer)
        print("EPOCH", i)
        while True:
            try:
                _, epoch_loss = sess.run([train, loss])

            except tf.errors.OutOfRangeError:  # Error given when out of data
                if i % 2 == 0:
                    # [train_accuaracy] = sess.run([accuracy])
                    # print("Step ", i, "training accuracy = %{}".format(train_accuaracy))
                    print(epoch_loss)
                break

我花了几个小时试图系统地弄清楚为什么我在运行这个模型时得到了 0 损失。

  • 特征 = 每个图像的文件位置列表(例如 ['\data\train\cat.0.jpg', /data\train\cat.1.jpg])
  • 标签 = [Batch_size, 1] one_hot 向量

最初我认为这是因为我的数据有问题。但是我在调​​整大小后查看了数据,图像看起来很好。

然后我尝试了一些不同的损失函数,因为我想也许我误解了 tensorflow 函数的softmax_cross_entropy作用,但这并没有解决任何问题。

我试过只运行“logits”部分来查看输出是什么。这只是一个小样本,数字对我来说似乎很好:

 [[0.06388957]
 [0.        ]
 [0.16969752]
 [0.24913025]
 [0.09961276]]

既然相应的标签是 0 或 1,那么softmax_cross_entropy函数应该能够计算这个损失吗?我不确定我是否遗漏了什么。任何帮助将不胜感激。

4

1 回答 1

0

记载

logits并且labels必须具有相同的形状,例如[batch_size, num_classes]和相同的 dtype(或者float16float32float64)。

既然你提到你的标签是“[Batch_size, 1] one_hot vector”,我会假设你的logitslabels都是 [Batch_size, 1] 形状。这肯定会导致零损失。从概念上讲,您只有 1 个类 ( num_classes=1),而且您不会错 ( loss=0)。

所以至少对你labels来说,你应该改造它:tf.one_hot(indices=labels, depth=num_classes)。你的预测logits也应该有一个形状[batch_size, num_classes]输出。

或者,您可以使用sparse_softmax_cross_entropy_with_logits,其中:

一个常见的用例是具有形状为 [batch_size, num_classes] 的 logits 和形状为 [batch_size] 的标签。但支持更高的维度。

于 2018-04-19T23:15:02.473 回答