内核大小和“相同”时在张量流中跨度的填充值公式是什么？

Question

在内核大小和跨度解码“相同”值时，张量流是否遵循任何通用公式

tf.keras.layers.Conv2D(hiddim_v * 4, kernel_size = 3, stride= 1, "same")

Answer 1

根据官方文档https://www.tensorflow.org/api_docs/python/tf/nn/convolution

If padding == "SAME": output_spatial_shape[i] = ceil(input_spatial_shape[i] / strides[i])
If padding == "VALID": output_spatial_shape[i] = ceil((input_spatial_shape[i] - (spatial_filter_shape[i]-1) * dilation_rate[i]) / strides[i]).

spatial_filter_shape是内核大小