2

我在 tensorflow 中训练 CNN，但程序似乎停留在第一个 tf.nn.conv2d 步骤。我已经从 keras 导入了 cifar 10 数据集并在 floydhub 中运行我的代码。我还没有开始会话，这只是计算图。 链接到完整的笔记本

这是卡住的部分：

# forward propagation

# convolution layer 1
c1 = tf.nn.conv2d(x_train, w1, strides = [1,1,1,1], padding = 'VALID')
# activation function for c1: relu
r1 = tf.nn.relu(c1)
# maxpooling
p1 = tf.nn.max_pool(r1, ksize = [1,2,2,1], strides = [1,2,2,1], padding = 'SAME')

# convolution layer 2
c2 = tf.nn.conv2d(p1, w2, strides = [1,1,1,1], padding='VALID')
# activation function for c2: relu
r2 = tf.nn.relu(c2) 
# maxpooling
p2 = tf.nn.max_pool(r2, ksize = [1,2,2,1], strides = [1,2,2,1], padding = 'SAME')

# flattening the previous max pool layer
l1 = tf.contrib.layers.flatten(p2)
# fully connected layer
final = tf.contrib.layers.fully_connected(l1, 10, activation_fn = None)

编辑：-

这就是我导入数据集的方式

# importing 50000 images of size 32x32x3
i = 0
# this list holds the images
img_base = []
for img in glob.glob("train\\*.png"):
    img_base.append(cv2.imread(img))

# x_train is a nx32x32x3 matrix of n no. of images
x_train = np.array(img_base[0:40000]).astype(np.float32)

用于训练图像和标签的占位符

# creating placeholders
x = tf.placeholder(tf.float32, [None, 32, 32, 3])
y = tf.placeholder(tf.float32, [None, 10])

权重初始化`

tf.reset_default_graph()

# creating weights
w1 = tf.get_variable('w1', [4,4,3,10], initializer=tf.contrib.layers.xavier_initializer())
w2 = tf.get_variable('w2', [4,4,10,15], initializer=tf.contrib.layers.xavier_initializer())
4

0 回答 0