张量流误差模型.拟合()

Question

你好，正在学习tensoflow和numpy。我正在尝试创建CNN图像分类模型。在

我的图像尺寸是28X28

这是我的模型：

        MODEL_NAME = 'ComputerVision-{}-{}.model'.format(LR, '6conv-basic') # 6conv layer
        import tensorflow as tf
        tf.reset_default_graph()



        convnet = input_data(shape=[None, IMG_SIZE, IMG_SIZE, 1], name='input')
        # layer 
        convnet = conv_2d(convnet, 28, 5, activation='relu')
        convnet = max_pool_2d(convnet, 5)
        # layer 
        convnet = conv_2d(convnet, (56, 5, activation='relu')
        convnet = max_pool_2d(convnet, 5)
        #layer 
        convnet = conv_2d(convnet, 112, 5, activation='relu')
        convnet = max_pool_2d(convnet, 5)
        # layer 
        convnet = conv_2d(convnet, 56, 5, activation='relu')
        convnet = max_pool_2d(convnet, 5)
        #layer 
        convnet = conv_2d(convnet, 28, 5, activation='relu')
        convnet = max_pool_2d(convnet, 5)
        #dense layer
        convnet = fully_connected(convnet, 784, activation='relu')

        convnet = dropout(convnet, 0.8)

        convnet = fully_connected(convnet, 2, activation='softmax')
        convnet = regression(convnet, optimizer='adam', learning_rate=LR, loss='categorical_crossentropy', name='targets')

 #my neural network model 
        model = tflearn.DNN(convnet, tensorboard_dir='log')

    # train and test set 
    train = train_data[:-500]#my train data 
    test = train_data[-500:]

        X = np.array([i[0] for i in train]).reshape(-1,IMG_SIZE,IMG_SIZE,1)
        Y = [i[1] for i in train]

        test_x = np.array([i[0] for i in test]).reshape(-1,IMG_SIZE,IMG_SIZE,1)
        test_y = [i[1] for i in test]

model.fit({'input': X}, {'targets': Y}, n_epoch=10, 
    validation_set=({'input': test_x}, {'targets': test_y}),  snapshot_step=200,show_metric=True,run_id=MODEL_NAME)

当我试图训练我的模型时，我遇到了一个错误：

似乎错误出在型号名称上

这是第一个错误

^{pr2}$

Answer 1

当使用tflearn调用model.fit()方法时，属性validation_set中的条目必须是一个元组。尝试这样做：

model.fit(X_inputs=X, Y_targets=Y, n_epoch=10, validation_set=(test_x, test_y),\
                    snapshot_step=200, show_metric=True, run_id=MODEL_NAME)

我希望它能起作用！
另外，请查看Deep Neural Network Model TFLearn docs here。在