张量流值错误：无法为张量 u'InputData/X：0' 提供形状值 （96， 50， 50）

Question

我是张量流和蟒蛇的新手。我正在尝试使用CNN运行肺癌检测代码。脚本如下：我正在尝试训练 CNN 模型。当我在训练时使用时，我遇到错误model.fit

    from tflearn.layers.core import input_data, dropout, fully_connected

from tflearn.layers.conv import conv_2d, max_pool_2d

from tflearn.layers.estimator import regression

from tflearn.data_preprocessing import ImagePreprocessing

from tflearn.data_augmentation import ImageAugmentation

img_prep = ImagePreprocessing()

img_prep.add_featurewise_zero_center()

img_prep.add_featurewise_stdnorm()

img_aug = ImageAugmentation()

img_aug.add_random_flip_leftright()

img_aug.add_random_rotation(max_angle=25.)

img_aug.add_random_blur(sigma_max=3.)

network = input_data(shape=[None, 50, 50, 1],

                     data_preprocessing=img_prep,

                     data_augmentation=img_aug)

network = conv_2d(network, 50, 3, activation='relu')

network = max_pool_2d(network, 2)

network = conv_2d(network, 64, 3, activation='relu')

network = conv_2d(network, 64, 3, activation='relu')

network = max_pool_2d(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)

model = tflearn.DNN(network, tensorboard_verbose=0, checkpoint_path='nodule-classifier.tfl.ckpt')

model.fit(X_train_images, Y_train_labels, n_epoch=100, shuffle=True, validation_set=(X_val_images, Y_val_labels),

          show_metric=True, batch_size=96, snapshot_epoch=True, 

          run_id='noduleclassifier')

model.save("nodule-classifier.tfl")

print("Network trained and saved as nodule-classifier.tfl!")

我正在尝试训练一个 CNN 模型。当我在训练时使用时，我得到一个错误 - >model.fit

Answer 1

该模型期望直径为 4 的张量。您必须向训练数据添加第四个维度。用X_train_images = np.expand_dims(X_train_images, axis=-1)扩展尺寸和 np.挤压以减小尺寸