Question

代码表：

https://github.com/wepe/MachineLearning/blob/master/DeepLearning%20Tutorials/cnn_LeNet/convolutional_mlp.py

运行CNN测试时出现错误。我尝试了一些方法，但没有工作。

代码：

def evaluate_lenet5(learning_rate=0.1, n_epochs=200,
                dataset='mnist.pkl.gz',
                nkerns=[20, 50], batch_size=500):
    rng = numpy.random.RandomState(23455)

将形状（batch_size，28 * 28）的光栅化图像矩阵重塑为4D张量，与我们的LeNetConvPoolLayer（28,28）兼容，是MNIST图像的大小。

# Load data
datasets = load_data(dataset)
train_set_x, train_set_y = datasets[0]
valid_set_x, valid_set_y = datasets[1]
test_set_x, test_set_y = datasets[2]

# Calculate the number of batches
n_train_batches = train_set_x.get_value(borrow=True).shape[0]
n_valid_batches = valid_set_x.get_value(borrow=True).shape[0]
n_test_batches = test_set_x.get_value(borrow=True).shape[0]
n_train_batches /= batch_size
n_valid_batches /= batch_size
n_test_batches /= batch_size

index = T.lscalar()  
x = T.matrix('x')   
y = T.ivector('y') 
layer0_input = x.reshape((batch_size, 1, 28, 28))
...

错误：

ValueError: cannot reshape array of size 392000 into shape (28,28)

这些信息（输入）显示在错误下方：

Toposort index: 41
Inputs types: [TensorType(float64, matrix), TensorType(int64, vector)]
Inputs shapes: [(500, 784), (2,)]
Inputs strides: [(6272, 8), (8,)]
Inputs values: ['not shown', array([28, 28], dtype=int64)]
Outputs clients: [[InplaceDimShuffle{x,x,0,1}(Reshape{2}.0)]]
HINT: Use the Theano flag 'exception_verbosity=high' for a debugprint and storage map footprint of this apply node.

392000 = bath_size（500）* 28 * 28，所以，我不知道为什么......

如果有人能解决这个问题，我非常感激。 THX！

ValueError：无法将大小为392000的数组重塑为形状（28,28）

0 个答案: