22 lines
1.3 KiB
JSON
22 lines
1.3 KiB
JSON
{
|
|
"type": "Separable Conv 2D Layer",
|
|
"definition": {
|
|
"text": "Depthwise separable 2D convolution. Separable convolution consists of first performing a depthwise spatial convolution (which acts on each input channel separately) followed by a pointwise convolution which mixes together the resulting output channels. The depthMultiplier argument controls how many output channels are generated per input channel in the depthwise step.",
|
|
"updated": 1613218940003
|
|
},
|
|
"paragraphs": [
|
|
{
|
|
"style": "Text",
|
|
"text": "Intuitively, separable convolutions can be understood as a way to factorize a convolution kernel into two smaller kernels, or as an extreme version of an Inception block.",
|
|
"updated": 1613218949720
|
|
},
|
|
{
|
|
"style": "List",
|
|
"text": "Input shape: 4D tensor with shape: [batch, channels, rows, cols] if data_format='channelsFirst' or 4D tensor with shape: [batch, rows, cols, channels] if data_format='channelsLast'."
|
|
},
|
|
{
|
|
"style": "List",
|
|
"text": "Output shape: 4D tensor with shape: [batch, filters, newRows, newCols] if data_format='channelsFirst' or 4D tensor with shape: [batch, newRows, newCols, filters] if data_format='channelsLast'. rows and cols values might have changed due to padding."
|
|
}
|
|
]
|
|
} |