Skip to main content
 首页 » 编程设计

python之从 OpenCV 将数据加载到 CNN

2024年12月31日9cloudgamer

我使用 OpenCV 将视频文件中的帧加载到数组中,然后使用 sklearn 将数据拆分为 X_train 和 X_test。

我的 X_train.shape 是 (363, 1, 40, 40, 15),目前我正在处理 4 个类,以及我正在使用的模型从这些数据中学习的代码如下:

    model = Sequential() 
    model.add(Conv3D(32, (3,3,3), activation='relu', input_shape=(1, 40, 40, 15), data_format='channels_first')) 
    model.add(MaxPooling3D(pool_size=(1, 2, 2), strides=(1, 2, 2))) 
    model.add(Conv3D(64, (3,3,3), activation='relu')) 
    model.add(MaxPooling3D(pool_size=(1, 2, 2), strides=(1, 2, 2))) 
    model.add(Conv3D(128, (3,3,3), activation='relu')) 
    model.add(Conv3D(128, (3,3,3), activation='relu')) 
    model.add(MaxPooling3D(pool_size=(1, 2, 2), strides=(1, 2, 2))) 
    model.add(Conv3D(256, (2,2,2), activation='relu')) 
    model.add(Conv3D(256, (2,2,2), activation='relu')) 
    model.add(MaxPooling3D(pool_size=(1, 2, 2), strides=(1, 2, 2))) 
 
    model.add(Flatten()) 
 
    model.add(Dense(1024)) 
    model.add(Dropout(0.5)) 
    model.add(Dense(1024)) 
    model.add(Dropout(0.5)) 
    model.add(Dense(4, activation='softmax')) 

我在尝试加载模型时遇到此错误:

ValueError: Negative dimension size caused by subtracting 2 from 1 for 'conv3d_44/convolution' (op: 'Conv3D') with input shapes: [?,25,1,1,256], [2,2,2,256,256]. 

有人可以帮助我吗?

请您参考如下方法:

它已在 StackOverflow 上多次讨论:参见 here或 here .根据您的卷积层和池化层参数,张量在每个 Conv3D 和 MaxPooling3D 之后被下采样。这是模型在损坏之前的样子:

Layer (type)                 Output Shape              Param #    
================================================================= 
conv3d_1 (Conv3D)            (None, 32, 38, 38, 13)    896        
_________________________________________________________________ 
max_pooling3d_1 (MaxPooling3 (None, 32, 19, 19, 13)    0          
_________________________________________________________________ 
conv3d_2 (Conv3D)            (None, 30, 17, 17, 64)    22528      
_________________________________________________________________ 
max_pooling3d_2 (MaxPooling3 (None, 30, 8, 8, 64)      0          
_________________________________________________________________ 
conv3d_3 (Conv3D)            (None, 28, 6, 6, 128)     221312     
_________________________________________________________________ 
conv3d_4 (Conv3D)            (None, 26, 4, 4, 128)     442496     
_________________________________________________________________ 
max_pooling3d_3 (MaxPooling3 (None, 26, 2, 2, 128)     0          
_________________________________________________________________ 
conv3d_5 (Conv3D)            (None, 25, 1, 1, 256)     262400     

张量 (None, 25, 1, 1, 256) 无法进一步下采样,因此 错误。

解决方案是调整 Conv3D 参数:要么使用 padding='same'(在这种情况下,张量形状在卷积后保留,仅在池化后减半层)或将过滤器大小从 3 减少到 2。

例子:

model = Sequential() 
model.add(Conv3D(32, (3,3,3), activation='relu', input_shape=(1, 40, 40, 15), data_format='channels_first', padding='same')) 
model.add(MaxPooling3D(pool_size=(1, 2, 2), strides=(1, 2, 2))) 
model.add(Conv3D(64, (3,3,3), activation='relu', padding='same')) 
model.add(MaxPooling3D(pool_size=(1, 2, 2), strides=(1, 2, 2))) 
model.add(Conv3D(128, (3,3,3), activation='relu', padding='same')) 
model.add(Conv3D(128, (3,3,3), activation='relu', padding='same')) 
model.add(MaxPooling3D(pool_size=(1, 2, 2), strides=(1, 2, 2))) 
model.add(Conv3D(256, (2,2,2), activation='relu', padding='same')) 
model.add(Conv3D(256, (2,2,2), activation='relu', padding='same')) 
model.add(MaxPooling3D(pool_size=(1, 2, 2), strides=(1, 2, 2))) 
 
model.add(Flatten()) 
 
model.add(Dense(1024)) 
model.add(Dropout(0.5)) 
model.add(Dense(1024)) 
model.add(Dropout(0.5)) 
model.add(Dense(4, activation='softmax')) 
 
model.summary()