Numpy ValueError:检查输入时出错:预期conv2d_16_输入有4个维度

Numpy ValueError:检查输入时出错:预期conv2d_16_输入有4个维度,numpy,image-processing,deep-learning,neural-network,conv-neural-network,Numpy,Image Processing,Deep Learning,Neural Network,Conv Neural Network,我正在尝试为我使用YLO检测到的每幅图像的图像数据训练一个cnn模型,并仅在specefic帧上应用cnn 使用的cnn medel是: # define our Convolutional Neural Network architecture from tensorflow.keras import layers model = Sequential() model.add(layers.Conv2D(32, (3, 3), padding="same", input_s

我正在尝试为我使用YLO检测到的每幅图像的图像数据训练一个cnn模型,并仅在specefic帧上应用cnn 使用的cnn medel是:

# define our Convolutional Neural Network architecture from tensorflow.keras import layers model = Sequential() model.add(layers.Conv2D(32, (3, 3), padding="same", input_shape=(32, 32, 3))) model.add(layers.Activation("relu")) model.add(layers.MaxPooling2D(pool_size=(2, 2), strides=(2, 2))) model.add(layers.Conv2D(32, (3, 3), padding="same")) model.add(layers.Activation("relu")) model.add(layers.MaxPooling2D(pool_size=(2, 2), strides=(2, 2))) model.add(layers.Conv2D(32, (3, 3), padding="same")) model.add(layers.Activation("relu")) model.add(layers.MaxPooling2D(pool_size=(2, 2), strides=(2, 2))) model.add(layers.Conv2D(32, (3, 3), padding="same")) model.add(layers.Activation("relu")) model.add(layers.MaxPooling2D(pool_size=(2, 2), strides=(2, 2))) model.add(layers.Conv2D(32, (3, 3), padding="same")) model.add(layers.Activation("relu")) model.add(layers.MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))



#model.add(layers.Conv2D(32, (15, 15), padding="same"))
#model.add(layers.Activation("relu"))
#model.add(layers.MaxPooling2D(pool_size=(2, 2), strides=(2, 2))) model.add(layers.Flatten()) model.add(layers.Dense(10)) model.add(layers.Activation("softmax"))
我犯了一个错误:

ValueError: Error when checking input: expected conv2d_16_input to have 4 dimensions, but got array with shape (1, 1, 1, 1, 1, 1, 1, 1775, 1, 1, 32, 32, 1, 1, 1)

我认为你最好把整个代码都发布出来,但从外观上看,你的模型输入有一些非常奇怪的输入形状,我建议你检查你的模型输入