我正在使用自己的图像管道构建二进制分类器。图像是178x65（wxh）灰度jpgs。它正确加载图像及其标签，并正确地适合所有图层大小，但由于某种原因，它总是为每个图像输出相同的预测（[1. 0.]）。谁能指出我正确的方向？
# Example on how to use the tensorflow input pipelines. The explanation can be found here ischlag.github.io.
import tensorflow as tf
import random
from tensorflow.python.framework import ops
from tensorflow.python.framework import dtypes
dataset_path = "./v5-tensorflow/"
test_labels_file = "test-labels.csv"
train_labels_file = "train-labels.csv"
test_set_size = 39
IMAGE_HEIGHT = 65
IMAGE_WIDTH = 178
NUM_CHANNELS = 1
BATCH_SIZE = 39
def encode_label(label):
if label == "kalli\n":
return [0, 1]
elif label == "francisco\n":
return [1, 0]
else:
print("SOMETHING WENT WRONG")
return [0, 0]
def read_label_file(file):
f = open(file, "r")
filepaths = []
labels = []
for line in f:
filepath, label = line.split(",")
filepaths.append(filepath)
labels.append(encode_label(label))
return filepaths, labels
# reading labels and file path
train_filepaths, train_labels = read_label_file(dataset_path + train_labels_file)
test_filepaths, test_labels = read_label_file(dataset_path + test_labels_file)
# transform relative path into full path
train_filepaths = [ dataset_path + fp for fp in train_filepaths]
test_filepaths = [ dataset_path + fp for fp in test_filepaths]
# convert string into tensors
train_images = ops.convert_to_tensor(train_filepaths, dtype=dtypes.string)
test_images = ops.convert_to_tensor(test_filepaths, dtype=dtypes.string)
train_labels = ops.convert_to_tensor(train_labels, dtype=dtypes.int32)
test_labels = ops.convert_to_tensor(test_labels, dtype=dtypes.int32)
# create input queues
train_input_queue = tf.train.slice_input_producer(
[train_images, train_labels],
shuffle=True)
test_input_queue = tf.train.slice_input_producer(
[test_images, test_labels],
shuffle=True)
# process path and string tensor into an image and a label
file_content = tf.read_file(train_input_queue[0])
train_image = tf.image.decode_jpeg(file_content, channels=NUM_CHANNELS)
train_label = train_input_queue[1]
file_content = tf.read_file(test_input_queue[0])
test_image = tf.image.decode_jpeg(file_content, channels=NUM_CHANNELS)
test_label = test_input_queue[1]
# define tensor shape
train_image.set_shape([IMAGE_HEIGHT, IMAGE_WIDTH, NUM_CHANNELS])
test_image.set_shape([IMAGE_HEIGHT, IMAGE_WIDTH, NUM_CHANNELS])
# collect batches of images before processing
# train_image_batch, train_label_batch
train_batch = tf.train.batch(
[train_image, train_label],
batch_size=BATCH_SIZE
#,num_threads=1
)
# test_image_batch, test_label_batch
test_batch = tf.train.batch(
[test_image, test_label],
batch_size=BATCH_SIZE
#,num_threads=1
)
x = tf.placeholder(tf.float32, shape=[None, 65, 178, 1], name="x")
y_ = tf.placeholder(tf.float32, shape=[None, 2], name="y_")
#
def weight_variable(shape, n):
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial, name=n)
def bias_variable(shape, n):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial, name=n)
def conv2d(x, W):
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
def max_pool_2x2(x):
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1], padding='SAME')
#
input_reshape = tf.reshape(x, [-1,65,178,1])
W_conv1 = weight_variable([5, 5, 1, 32], "w1")
b_conv1 = bias_variable([32], "b1")
h_conv1 = tf.nn.relu(conv2d(input_reshape, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1) # 33x89x32
#
W_conv2 = weight_variable([5, 5, 32, 64], "w2")
b_conv2 = bias_variable([64], "b2")
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2) # now 17x45x64
W_conv3 = weight_variable([5, 5, 64, 128], "w3")
b_conv3 = bias_variable([128], "b3")
h_conv3 = tf.nn.relu(conv2d(h_pool2, W_conv3) + b_conv3)
h_pool3 = max_pool_2x2(h_conv3)# 9x23x128
W_conv4 = weight_variable([5, 5, 128, 256], "w4")
b_conv4 = bias_variable([256], "b4")
h_conv4 = tf.nn.relu(conv2d(h_pool3, W_conv4) + b_conv4)
h_pool4 = max_pool_2x2(h_conv4) # 5x12x256
W_fc1 = weight_variable([5 * 12 * 256, 5120], "w5")
b_fc1 = bias_variable([5120], "b5")
h_pool4_flat = tf.reshape(h_pool4, [-1, 5*12*256])
h_fc1 = tf.nn.relu(tf.matmul(h_pool4_flat, W_fc1) + b_fc1) # 1x5120
W_fc2 = weight_variable([5120, 2], "w6")
b_fc2 = bias_variable([2], "b6") # 1x2
y_conv = tf.nn.softmax(tf.matmul(h_fc1, W_fc2) + b_fc2, name="softmax")
y_clipped = tf.clip_by_value(y_conv, 1e-10, 0.9999999)
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y_clipped), reduction_indices=[1]))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_clipped, 1), tf.argmax(y_, 1), name="correct")
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32), name="accuracy")
saver = tf.train.Saver()
print("input pipeline ready")
with tf.Session() as sess:
# initialize the variables
sess.run(tf.global_variables_initializer())
# initialize the queue threads to start to shovel data
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(coord=coord)
print("from the train set:")
for i in range(62):
batch = sess.run(train_batch)
if i % 3 == 0:
train_accuracy = accuracy.eval(feed_dict={
x:batch[0], y_: batch[1]
})
print("step %d, training accuracy %.2f" % (i, train_accuracy))
train_step.run(feed_dict={x: batch[0], y_: batch[1]})
saver.save(sess, "model.ckpt")
tf.train.write_graph(sess.graph_def, '', 'graph.pb')
t_batch = sess.run(test_batch)
print("test accuracy %g" % accuracy.eval(feed_dict={
x: t_batch[0], y_: t_batch[1]
}))
# stop our queue threads and properly close the session
coord.request_stop()
coord.join(threads)
sess.close()