Computes a 3-D convolution given 5-D input and filter tensors.
In signal processing, cross-correlation is a measure of similarity of two waveforms as a function of a time-lag applied to one of them. This is also known as a sliding dot product or sliding inner-product.
Our Conv3D implements a form of cross-correlation.
Args:
input: A Tensor. Must be one of the following types: float32, float64, int64, int32, uint8, uint16, int16, int8, complex64, complex128, qint8, quint8, qint32, half. Shape [batch, in_depth, in_height, in_width, in_channels]. filter: A Tensor. Must have the same type as input. Shape [filter_depth, filter_height, filter_width, in_channels, out_channels]. in_channels must match between input and filter. strides: A list of ints that has length >= 5. 1-D tensor of length 5. The stride of the sliding window for each dimension of input. Must have strides[0] = strides[4] = 1. padding: A string from: “SAME”, “VALID”. The type of padding algorithm to use. name: A name for the operation (optional). Returns:
input: A Tensor. Must be one of the following types: float32, float64, int64, int32, uint8, uint16, int16, int8, complex64, complex128, qint8, quint8, qint32, half. Shape [batch, depth, rows, cols, channels] tensor to pool over. ksize: A list of ints that has length >= 5. 1-D tensor of length 5. The size of the window for each dimension of the input tensor. Must have ksize[0] = ksize[4] = 1. strides: A list of ints that has length >= 5. 1-D tensor of length 5. The stride of the sliding window for each dimension of input. Must have strides[0] = strides[4] = 1. padding: A string from: “SAME”, “VALID”. The type of padding algorithm to use. name: A name for the operation (optional). Returns:
A Tensor. Has the same type as input. The average pooled output tensor.
input: A Tensor. Must be one of the following types: float32, float64, int64, int32, uint8, uint16, int16, int8, complex64, complex128, qint8, quint8, qint32, half. Shape [batch, depth, rows, cols, channels] tensor to pool over. ksize: A list of ints that has length >= 5. 1-D tensor of length 5. The size of the window for each dimension of the input tensor. Must have ksize[0] = ksize[4] = 1. strides: A list of ints that has length >= 5. 1-D tensor of length 5. The stride of the sliding window for each dimension of input. Must have strides[0] = strides[4] = 1. padding: A string from: “SAME”, “VALID”. The type of padding algorithm to use. name: A name for the operation (optional). Returns:
A Tensor. Has the same type as input. The max pooled output tensor.
到这个阶段,时间维上帧的个数已经很小了, (3 for gray, gradient-x, gradient-y, and 2 for optflow-x and optflow-y)。在这一层,我们只在空间维度上面卷积,这时候我们使用的核是7x4,然后输出的特征maps就被减小到1x1的大小。而C6层就包含有128个特征map,每个特征map与S5层中所有78(13x6)个特征maps全连接,这样每个特征map就是1x1,也就是一个值了,而这个就是最终的特征向量了。共128维。