Question

第一次遇到这样的问题。测试tflearn的神经网络会产生错误。尝试测试此代码时，Python会生成错误。 conv_2d没有这样的问题。

我的代码： import numpy as np import random import tflearn from tflearn.layers.core import input_data, dropout, fully_connected from tflearn.layers.conv import conv_3d, max_pool_3d from tflearn.layers.estimator import regression



trainX = [[[random.randint(0,3) for col in range(15)] for row in range(15)] for x in range(50)]
testX = [[[random.randint(0,3) for col in range(15)] for row in range(15)] for x in range(10)]

trainY = [[0,1] for x in range(100)]
testY = [[0,1] for x in range(10)]


idnn = 'test_cnn'

network = input_data(shape=[None, 15, 15,15, 1])
network = conv_3d(network, 10, 3, activation='relu')

network = max_pool_3d(network, 2)
network = conv_3d(network, 32, 3, activation='relu')
network = conv_3d(network, 32, 3, activation='relu')

network = max_pool_3d(network, 2)
network = fully_connected(network, 512, activation='relu')
network = dropout(network, 0.5)
network = fully_connected(network, 2, activation='softmax')
network = regression(network, optimizer='adam',
                     loss='categorical_crossentropy',
                     learning_rate=0.001)



# Train using classifier
model = tflearn.DNN(network, tensorboard_verbose=0)
model.fit(trainX, trainY, n_epoch=10, shuffle=True, validation_set=(testX, testY),
          show_metric=True, batch_size=5, run_id= idnn)    
pred = model.predict(testX)

trainX = [[[random.randint(0,3) for col in range(15)] for row in range(15)] for x in range(50)] testX = [[[random.randint(0,3) for col in range(15)] for row in range(15)] for x in range(10)] trainY = [[0,1] for x in range(100)] testY = [[0,1] for x in range(10)] idnn = 'test_cnn' network = input_data(shape=[None, 15, 15,15, 1]) network = conv_3d(network, 10, 3, activation='relu') network = max_pool_3d(network, 2) network = conv_3d(network, 32, 3, activation='relu') network = conv_3d(network, 32, 3, activation='relu') network = max_pool_3d(network, 2) network = fully_connected(network, 512, activation='relu') network = dropout(network, 0.5) network = fully_connected(network, 2, activation='softmax') network = regression(network, optimizer='adam', loss='categorical_crossentropy', learning_rate=0.001) # Train using classifier model = tflearn.DNN(network, tensorboard_verbose=0) model.fit(trainX, trainY, n_epoch=10, shuffle=True, validation_set=(testX, testY), show_metric=True, batch_size=5, run_id= idnn) pred = model.predict(testX)

这在尝试测试代码时会出现错误。

    ValueError: Cannot feed value of shape (50, 15, 15) for Tensor 'InputData/X:0', which has shape '(?, 15, 15, 15, 1)'

可能是什么问题？请有人帮忙。

Answer 1

您的trainX和testX有形状（50,15,15）。但是，在

network = input_data(shape=[None, 15, 15,15, 1])

您指定输入的形状为（None，15,15,15,1）。这些形状不匹配。 None可以表示任何数字，但形状应匹配。

例如，您可以将trainX和testX变形（50,15,15,15,1）。

Answer 2

让我们看看，conv_3d网络是什么？

来自tflearn文档的信息。

输入

5-D Tensor [batch, in_depth, in_height, in_width, in_channels]。

输出

5-D Tensor [filter_depth, filter_height, filter_width, in_channels, out_channels].

trainX和testX数据的大小应相同。因为您使用testX中的validation_set数据。

您的trainX和testX数据看起来像2D数据集。 50x(15,15)，10x(15,15) 如果您想使用conv_3d，则必须使train和test数据的大小相同。（50x(15,15)，50x(15,15)）。

此外，我发现您的目标数据trainY与您的列车数据trainX的大小不同。

tflearn 3d tensor - ValueError：无法提供形状值（50,15,15）

2 个答案: