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()
