【发布时间】：2016-11-06 16:48:22
【问题描述】：
这是我正在使用的代码：
import tensorflow as tf
import numpy as np
from PIL import Image
from os import listdir
nodes_l1 = 500
nodes_l2 = 100
nodes_l3 = 500
num_batches = 20
num_epochs = 50
# Array of file dirs
human_file_array = listdir('human/')
human_file_array = [['human/'+human_file_array[i],[1,0]] for i in range(len(human_file_array))]
cucumber_file_array = listdir('cucumber/')
cucumber_file_array = [['cucumber/'+cucumber_file_array[i],[0,1]] for i in range(len(cucumber_file_array))]
file_array_shuffled = human_file_array + cucumber_file_array
np.random.shuffle(file_array_shuffled)
htest_file_array = listdir('human_test/')
htest_file_array = [['human_test/'+htest_file_array[i],[1,0]] for i in range(len(htest_file_array))]
ctest_file_array = listdir('cucumber_test/')
ctest_file_array = [['cucumber_test/'+ctest_file_array[i],[0,1]] for i in range(len(ctest_file_array))]
test_file_array = ctest_file_array + htest_file_array
np.random.shuffle(test_file_array)
input_data = tf.placeholder('float', [None, 250*250*3]
output_data = tf.placeholder('float')
hl1_vars = {
'weight': tf.Variable(tf.random_normal([250*250*3, nodes_l1])),
'bias': tf.Variable(tf.random_normal([nodes_l1]))
}
hl2_vars = {
'weight': tf.Variable(tf.random_normal([nodes_l1, nodes_l2])),
'bias': tf.Variable(tf.random_normal([nodes_l2]))
}
hl3_vars = {
'weight': tf.Variable(tf.random_normal([nodes_l2, nodes_l3])),
'bias': tf.Variable(tf.random_normal([nodes_l3]))
}
output_layer_vars = {
'weight': tf.Variable(tf.random_normal([nodes_l3, 2])),
'bias': tf.Variable(tf.random_normal([2]))
}
layer1 = tf.add(tf.matmul(input_data, hl1_vars['weight']),hl1_vars['bias'])
layer1 = tf.nn.softmax(layer1)
layer2 = tf.add(tf.matmul(layer1, hl2_vars['weight']), hl2_vars['bias'])
layer2 = tf.nn.softmax(layer2)
layer3 = tf.add(tf.matmul(layer2, hl3_vars['weight']), hl3_vars['bias'])
layer3 = tf.nn.softmax(layer3)
output = tf.add(tf.matmul(layer3, output_layer_vars['weight']), output_layer_vars['bias'])
output = tf.nn.softmax(output)
def convert_image(path):
with Image.open(path) as img:
img = img.resize((250,250))
img = img.convert('RGB')
return img
def train_network():
#prediction = output
cost = tf.reduce_sum(tf.nn.sigmoid_cross_entropy_with_logits(output, output_data)) # output is the prediction, output_data is key
optimizer = tf.train.AdamOptimizer().minimize(cost)
with tf.Session() as sess:
sess.run(tf.initialize_all_variables())
saver = tf.train.Saver()
for epoch in range(num_epochs):
epoch_error = 0
batch_size = int((len(file_array_shuffled)/num_batches))
for i in range(num_batches):
path_var = []
key_var = []
img_var = []
#Still Filename Batch!!
batch_file_array = file_array_shuffled[batch_size*i:(batch_size*i)+batch_size] #batch1['file&val array']['val']
for batch_val in batch_file_array:
path_var.append(batch_val[0])
key_var.append(batch_val[1])
#FROM HERE ON path_var AND key_var HAVE MATCHING INDEXES DO NOT RANDOMIZE!!!
#This section here is complicated!
for path in path_var:
img = convert_image(path)
img_var.append(np.reshape(np.array(img), 250*250*3))
#print np.shape(img_var),np.shape(key_var) #img_var is array of size (batch#, 64*64*3) key_var is the key [human, cucumber]
#End of complicationimage conversion
_,c = sess.run([optimizer, cost], feed_dict={input_data:img_var, output_data:key_var})
epoch_error += c
#print "Batch",i+1,"done out of",num_batches
print "Epoch",epoch+1,"completed out of",num_epochs,"\tError",epoch_error
save_path = saver.save(sess, "model.ckpt")
train_network()
def use_network():
#prediction = output
with tf.Session() as sess:
sess.run(tf.initialize_all_variables())
saver = tf.train.Saver()
saver.restore(sess, "model.ckpt")
for test_file in test_file_array:
#print test_file
img = np.reshape(np.array(convert_image(test_file[0])), 250*250*3)
result = output.eval(feed_dict={input_data:[img]})
print result,tf.argmax(result,1).eval(),test_file[1]
use_network()
由于我还是新手使用 tensorflow，我认为尝试创建一个可以识别人类和黄瓜之间差异的程序是一个好主意。我从 Image-Net 中提取图像，并将人类图片放入 human/ 并将黄瓜照片放入 cucumber/
我创建了一个我认为程序正在执行的步骤的列表：
创建文件路径和键的数组，然后对其进行洗牌。
批量创建文件路径。
批处理中的文件路径被转换为图像，调整为 250x250，并添加到图像批处理数组中。（此时键和图像仍然对齐）。
图像批处理和密钥批处理输入数组。
在所有 epoch 结束时，它针对每个图像中的 10 个图像测试网络。
当我运行 use_network() 时，我在控制台中得到这个输出：
[[ 0.53653401 0.46346596]] [0] [0, 1]
[[ 0.53653401 0.46346596]] [0] [0, 1]
[[ 0.53653401 0.46346596]] [0] [0, 1]
[[ 0.53653401 0.46346596]] [0] [1, 0]
[[ 0.53653401 0.46346596]] [0] [1, 0]
[[ 0.53653401 0.46346596]] [0] [0, 1]
[[ 0.53653401 0.46346596]] [0] [1, 0]
[[ 0.53653401 0.46346596]] [0] [1, 0]
[[ 0.53653401 0.46346596]] [0] [1, 0]
[[ 0.53653401 0.46346596]] [0] [0, 1]
[[ 0.53653401 0.46346596]] [0] [1, 0]
[[ 0.53653401 0.46346596]] [0] [0, 1]
[[ 0.61422414 0.38577583]] [0] [1, 0]
[[ 0.53653401 0.46346596]] [0] [0, 1]
[[ 0.53653401 0.46346596]] [0] [1, 0]
[[ 0.53653401 0.46346596]] [0] [1, 0]
[[ 0.53653401 0.46346596]] [0] [0, 1]
[[ 0.53653401 0.46346596]] [0] [0, 1]
[[ 0.53653401 0.46346596]] [0] [0, 1]
[[ 0.53653401 0.46346596]] [0] [1, 0]
第一个数组是输出节点，第二个数组是输出的 tf.argmax()，第三个是预期的。
实际的学习似乎也很小，这是学习的输出：
Epoch 1 completed out of 50 Error 3762.83390808
Epoch 2 completed out of 50 Error 3758.51748657
Epoch 3 completed out of 50 Error 3753.70425415
Epoch 4 completed out of 50 Error 3748.32539368
Epoch 5 completed out of 50 Error 3742.45524597
Epoch 6 completed out of 50 Error 3736.21272278
Epoch 7 completed out of 50 Error 3729.56756592
...
Epoch 45 completed out of 50 Error 3677.34605408
Epoch 46 completed out of 50 Error 3677.34388733
Epoch 47 completed out of 50 Error 3677.34150696
Epoch 48 completed out of 50 Error 3677.3391571
Epoch 49 completed out of 50 Error 3677.33673096
Epoch 50 completed out of 50 Error 3677.33418274
我已尝试执行以下操作来尝试更改：
缩小图像，例如 32x32 和/或黑白图像。看看较小的图像是否会导致预测发生变化。
将 reduce_sum 和 reduce_mean 之间的成本方程以及 sigmoid_cross_entropy 之间的内部方程更改为 softmax_cross_entropy。
我有一些关于它为什么不起作用的想法，它们如下：
只是糟糕的代码
输入数据太大，没有足够的节点/层来处理。
图像和相关密钥在某处被打乱。
【问题讨论】：
-
尝试降低学习率。根据我的经验，这是导致此问题的最常见原因。
标签： tensorflow batching