Python ValueError:无法为具有形状“(?,224,224,3)”的张量“占位符_3:0”提供形状(224,224,3)的值
我是Tensorflow的新手,我尝试训练我的CNN模型,以便将来对人脸进行分类。我有一个56个人的图像数据集,他们被裁剪的脸是numpy数组,形状为[-1224224,3]和float32类型。当我试着把它输入tensorflow时 我只是附上我的X列和Y列的样子,以便输入tensorflow 我得到了典型的错误值error:cannotfeed形状2242242243的值,用于张量'Placeholder_3:0',它有形状'?,2242243'。这似乎很容易理解,但我不知道如何修改我的代码使其工作 我的Tensorflow代码在这里Python ValueError:无法为具有形状“(?,224,224,3)”的张量“占位符_3:0”提供形状(224,224,3)的值,python,tensorflow,convolution,Python,Tensorflow,Convolution,我是Tensorflow的新手,我尝试训练我的CNN模型,以便将来对人脸进行分类。我有一个56个人的图像数据集,他们被裁剪的脸是numpy数组,形状为[-1224224,3]和float32类型。当我试着把它输入tensorflow时 我只是附上我的X列和Y列的样子,以便输入tensorflow 我得到了典型的错误值error:cannotfeed形状2242242243的值,用于张量'Placeholder_3:0',它有形状'?,2242243'。这似乎很容易理解,但我不知道如何修改我的代码
import tensorflow as tf
config = tf.ConfigProto()
config.gpu_options.allocator_type = 'BFC'
#config.gpu_options.allow_growth = True
config.gpu_options.per_process_gpu_memory_fraction = 0.6
n_classes = 56
batch_size = 1
hm_epochs = 100
#x = tf.placeholder('float', [None, 150528])
x = tf.placeholder('float', [None, 224,224,3])
y = tf.placeholder('float')
keep_rate = 0.8
keep_prob = tf.placeholder(tf.float32)
def conv2d(x, W):
return tf.nn.conv2d(x, W, strides=[1,1,1,1], padding='SAME')
def maxpool2d(x):
# size of window movement of window
return tf.nn.max_pool(x, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME')
def convolutional_neural_network(x):
weights = {'W_conv1':tf.Variable(tf.random_normal([5,5,3,32])),
'W_conv2':tf.Variable(tf.random_normal([5,5,32,64])),
'W_fc':tf.Variable(tf.random_normal([224*224*3,1024])),
'out':tf.Variable(tf.random_normal([1024, n_classes]))}
biases = {'b_conv1':tf.Variable(tf.random_normal([32])),
'b_conv2':tf.Variable(tf.random_normal([64])),
'b_fc':tf.Variable(tf.random_normal([1024])),
'out':tf.Variable(tf.random_normal([n_classes]))}
x = tf.reshape(x, shape=[-1, 224, 224, 3])
#x = train_X
#creating the first layer of CNN
conv1 = tf.nn.relu(conv2d(x, weights['W_conv1']) + biases['b_conv1']) # activation function 1
conv1 = maxpool2d(conv1)
#creating the second layer of CNN
conv2 = tf.nn.relu(conv2d(conv1, weights['W_conv2']) + biases['b_conv2']) # activation function 2
conv2 = maxpool2d(conv2)
fc = tf.reshape(conv2,[-1, 224*224*3])
fc = tf.nn.relu(tf.matmul(fc, weights['W_fc'])+biases['b_fc'])
fc = tf.nn.dropout(fc, keep_rate)
output = tf.matmul(fc, weights['out'])+biases['out']
return output
def train_neural_network(x):
i = 0
prediction = convolutional_neural_network(x)
cost = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits(logits=prediction,labels=y) )
optimizer = tf.train.AdamOptimizer().minimize(cost)
with tf.Session(config = config) as sess:
sess.run(tf.global_variables_initializer())
for epoch in range(hm_epochs):
epoch_loss = 0
for _ in range(int(len(train_X)/batch_size)):
_, c = sess.run([optimizer, cost], feed_dict={x: train_X[i:i+batch_size], y: train_y[i:i+batch_size]}) #HERE IS THE ERROR
epoch_loss += c
i += 100
print('Epoch', epoch, 'completed out of',hm_epochs,'loss:',epoch_loss)
train_neural_network(x)
如果有人能帮我把一切弄清楚,我会很高兴的。提前感谢你的帮助。顺便说一句,我需要以GPU不会给我OOM的方式批量处理数据。因为我可以改变进料方式以排除配料,除了OOM错误,它工作正常。有趣的故事是,当我重新启动内核并再次运行它的时候。发生了另一个错误-InvalidArgumentError回溯请参见上文:重塑的输入是一个具有200704个值的张量,但请求的形状需要150528的倍数。200704根本不能在这里,因为这是224*224*4,而我只有224*224*3fc层的形状不正确 W_fc':tf.Variabletf.random_normal[224*224*31024] W_fc':tf.Variabletf.random_normal[56*56*641024] fc=tf.v2,[-1224*224*3] fc=tf.v2,[-1,56*56*64] 当您对输入图像应用卷积和最大池时,您将获得以下大小的特征贴图 输入图像:224x224x3 | conv1 224x224x32 | maxpool 112x112x32 | conv2 112x112x64 | maxpool 56x56x64 我修复了你的代码如上所述,它的工作。
请试一试。将您的train_X重塑为[-1224224,3],您正在输入一个输入,因此它应该是[12242224,3],而不是[224224,3]