āļ„āļđāđˆāļĄāļ·āļ­āļ—āļēāļ‡āđ€āļ—āļ„āļ™āļīāļ„

Convolution āļ—āļĩāđˆāđāļĒāļāļŠāđˆāļ§āļ™āļĨāļķāļāđ„āļ”āđ‰

A depthwise separable convolution splits an ordinary convolution layer into two cheaper steps: a depthwise step that filters each channel on its own, and a 1 by 1 pointwise step that mixes channels.

āļŸāļąāļ‡āļ„āļģāđāļ™āļ°āļ™āļģāļ™āļĩāđ‰āļšāļĢāļĢāļĒāļēāļĒāđ‚āļ”āļĒ AI · ~8 min

āļšāļ™āļŦāļ™āđ‰āļēāļ™āļĩāđ‰āļ­āđˆāļēāļ™ 9 āļ™āļēāļ—āļĩ
  1. āļ āļēāļžāļĢāļ§āļĄ
  2. āļ›āļĢāļ°āđ€āļ”āđ‡āļ™āļŠāļģāļ„āļąāļ
  3. āđ€āļˆāļēāļ°āļĨāļķāļ
  4. Counting the cost of one layer
  5. āļāļēāļĢāđƒāļŠāđ‰āļ‡āļēāļ™āļˆāļĢāļīāļ‡āđƒāļ™āđ‚āļĨāļāđāļŦāđˆāļ‡āļ„āļ§āļēāļĄāđ€āļ›āđ‡āļ™āļˆāļĢāļīāļ‡
  6. āļ­āļ™āļēāļ„āļ•āļ‚āļ­āļ‡āļāļēāļĢāđ‚āļ™āđ‰āļĄāļ™āđ‰āļēāļ§āđƒāļˆāļ—āļĩāđˆāđāļĒāļāļˆāļēāļāļāļąāļ™āđƒāļ™āđ€āļŠāļīāļ‡āļĨāļķāļ
  7. āļāļēāļĢāļ™āļģāđ„āļ›āļ›āļāļīāļšāļąāļ•āļī
  8. āļ—āļĩāđˆāļĄāļēāđāļĨāļ°āļ­āđˆāļēāļ™āđ€āļžāļīāđˆāļĄāđ€āļ•āļīāļĄ
  9. āļŠāļģāļĢāļ§āļˆāļ•āđˆāļ­āđ„āļ›
  10. āļ„āļģāļ–āļēāļĄāļ—āļĩāđˆāļžāļšāļšāđˆāļ­āļĒ

āļ āļēāļžāļĢāļ§āļĄ

With 3 by 3 kernels it needs roughly 8 to 9 times less computation, which is why it underpins mobile vision networks such as MobileNet and Xception.

āļ›āļĢāļ°āđ€āļ”āđ‡āļ™āļŠāļģāļ„āļąāļ

  1. A depthwise separable convolution replaces one standard convolution with a per-channel depthwise filter followed by a 1 by 1 pointwise convolution.
  2. Its cost relative to a standard convolution is 1/N plus 1/k squared, about one ninth for 3 by 3 kernels.
  3. MobileNet's depthwise separable version lost about 1 point of ImageNet accuracy while using roughly one eighth of the multiply-adds of a full-convolution version.
  4. Laurent Sifre developed the operation at Google Brain in 2013, and Xception and MobileNets popularized it in 2016 and 2017.
  5. Depthwise layers have high memory traffic per operation, so real speedups depend on the hardware and runtime, not just operation counts.

āđ€āļˆāļēāļ°āļĨāļķāļ

A convolution layer in an image network slides small filters over a feature map, a grid of values with a height, a width and a number of channels. The input image has three channels, red, green and blue, and deeper layers commonly have hundreds of channels, each detecting some learned pattern. A standard convolution does two jobs at once. Each filter looks at a small spatial neighborhood, such as 3 by 3 pixels, and it looks at every input channel together, so a single filter both finds spatial patterns and combines channels. If there are M input channels and N output channels, the layer needs N separate filters, each of size 3 by 3 by M.

A depthwise separable convolution splits those two jobs. First, a depthwise convolution applies one small filter to each input channel separately, so channel 1 gets its own 3 by 3 filter, channel 2 gets its own, and so on, with no mixing between channels. Second, a pointwise convolution, which is a 1 by 1 convolution, combines the channels: at every pixel position it computes N weighted sums of the M depthwise outputs. The result has the same shape as a standard convolution's output, but the work is done in a cheaper, factorized way. The Xception paper notes that frameworks such as TensorFlow and Keras call this operation a separable convolution, which should not be confused with a spatially separable convolution that splits a 3 by 3 filter into 3 by 1 and 1 by 3 parts.

The savings follow from counting multiplications. For a feature map of size D_F by D_F, a standard convolution with a D_K by D_K kernel costs D_K x D_K x M x N x D_F x D_F multiply-adds. The depthwise step costs D_K x D_K x M x D_F x D_F, and the pointwise step costs M x N x D_F x D_F. Dividing the sum by the original gives 1/N + 1/D_K squared. With a 3 by 3 kernel and many output channels, that is just over one ninth, so the MobileNet paper describes the saving as 8 to 9 times less computation. Its worked example, an internal layer with 512 input and output channels on a 14 by 14 map, drops from 462 million multiply-adds and 2.36 million parameters to 52.3 million multiply-adds and 0.27 million parameters.

The idea has a short, well-documented history. According to the Xception paper, Laurent Sifre developed depthwise separable convolutions during a Google Brain internship in 2013, tested them in AlexNet, presented an overview at ICLR 2014 and reported detailed results in his thesis. Early Inception networks used one as their first layer. In October 2016 Francois Chollet posted Xception, which reinterpreted Inception modules as a step between ordinary and depthwise separable convolution and built an entire network from the latter. In April 2017 Andrew Howard and colleagues at Google posted MobileNets, which used depthwise separable layers everywhere except the first layer and added width and resolution multipliers to trade accuracy for speed. MobileNetV2, posted in January 2018, wrapped the depthwise step in an inverted residual block with a linear bottleneck. ConvNeXt, posted by Facebook AI Research in January 2022, showed that 7 by 7 depthwise convolutions help a modernized ResNet compete with vision transformers.

The accuracy cost is usually modest. MobileNet's own comparison found that a version built from full convolutions reached 71.7% ImageNet top-1 accuracy with 4,866 million multiply-adds and 29.3 million parameters, while the depthwise separable version reached 70.6% with 569 million multiply-adds and 4.2 million parameters: about 1 point of accuracy for roughly an eighth of the computation. Xception showed the reverse case: at a similar parameter count to Inception V3, building from depthwise separable layers improved ImageNet accuracy slightly and improved results more on Google's internal JFT dataset of 350 million images and 17,000 classes. Other alternatives to the standard convolution include grouped convolutions, which mix channels only within groups, and spatially separable kernels, but depthwise separable layers became the default building block of mobile vision models.

The main limitation is that fewer multiply-adds do not always mean faster code. The ShuffleNet V2 paper argued that speed also depends on memory access, and classified depthwise convolution with element-wise operations because it has a high ratio of memory access to computation. On hardware tuned for large matrix multiplications, such as data-center GPUs, a depthwise layer can therefore run well below the speed its operation count suggests. MobileNet's authors designed around this by putting 95% of computation time in 1 by 1 convolutions, which map directly to highly optimized matrix multiplication routines, with the depthwise layers holding about 3% of multiply-adds and 1% of parameters. A second limitation is capacity: depthwise filters have very few parameters, which is why MobileNet used little or no weight decay on them and MobileNetV2 expands channels before the depthwise step.

In practice, depthwise separable convolutions are free to use and built into every major framework. In PyTorch, a depthwise convolution is an ordinary Conv2d layer whose groups argument equals the number of input channels, followed by a Conv2d with a 1 by 1 kernel. TensorFlow and Keras offer it directly as a separable convolution layer. The main practical work is measuring real latency on the target device, because the theoretical saving only appears when the hardware and runtime handle depthwise layers efficiently.

04āļ•āļąāļ§āļ­āļĒāđˆāļēāļ‡āļāļēāļĢāļ—āļģāļ‡āļēāļ™

Counting the cost of one layer

  1. Take a layer with a 14 by 14 feature map, 512 input channels, 512 output channels and a 3 by 3 kernel.

  2. Standard convolution: 3 x 3 x 512 x 512 x 14 x 14 is about 462 million multiply-adds, with 3 x 3 x 512 x 512, about 2.36 million weights.

  3. Depthwise step: 3 x 3 x 512 x 14 x 14 is about 0.9 million multiply-adds, with 4,608 weights.

  4. Pointwise step: 512 x 512 x 14 x 14 is about 51.4 million multiply-adds, with 262,144 weights.

  5. Add the two steps: about 52.3 million multiply-adds and about 0.27 million weights.

  6. Divide: 52.3 / 462 is about 0.113, matching 1/512 + 1/9.

āļĄāļąāļ™āđāļŠāļ”āļ‡āđƒāļŦāđ‰āđ€āļŦāđ‡āļ™āļ­āļ°āđ„āļĢ

The learner reproduces the MobileNet paper's Table 3 figures, about 8.8 times fewer multiply-adds and parameters, and sees that the pointwise step now holds almost all of the cost, which is why fast 1 by 1 convolution matters for these networks.

āļāļēāļĢāđƒāļŠāđ‰āļ‡āļēāļ™āļˆāļĢāļīāļ‡āđƒāļ™āđ‚āļĨāļāđāļŦāđˆāļ‡āļ„āļ§āļēāļĄāđ€āļ›āđ‡āļ™āļˆāļĢāļīāļ‡

On-phone image classification: MobileNetV2 reached 72.0% ImageNet top-1 accuracy with 3.4 million parameters and 300 million multiply-adds, running in about 75 milliseconds on one large core of a Google Pixel 1 phone with TensorFlow Lite.

Mobile object detection: the MobileNetV2 paper pairs the network with SSDLite, a detector that also uses depthwise separable layers, and reports it is 20 times more efficient and 10 times smaller than YOLOv2 while scoring higher on COCO.

Tiny models for constrained hardware: the original MobileNet paper's 0.25 width version has about 0.5 million parameters and 41 million multiply-adds, while still reaching 50.6% ImageNet accuracy.

Large-scale classification: Google's Xception replaced Inception modules with depthwise separable convolutions and, with slightly fewer parameters than Inception V3, scored 79.0% versus 78.2% top-1 on ImageNet.

Modern convolutional networks: ConvNeXt (2022), from Facebook AI Research, uses 7 by 7 depthwise convolutions to mix spatial information, separating spatial and channel mixing in a way its authors compare to vision transformers.

āļ­āļ™āļēāļ„āļ•āļ‚āļ­āļ‡āļāļēāļĢāđ‚āļ™āđ‰āļĄāļ™āđ‰āļēāļ§āđƒāļˆāļ—āļĩāđˆāđāļĒāļāļˆāļēāļāļāļąāļ™āđƒāļ™āđ€āļŠāļīāļ‡āļĨāļķāļ

Depthwise separable convolutions remain a standard building block, but the questions around them have shifted from operation counts to measured speed. The ShuffleNet V2 work in 2018 showed that memory access and fragmentation can dominate runtime in lightweight networks, and the practical answer has been to design models with latency measured on the real target device rather than estimated from multiply-adds. The operation has also found a role beyond mobile models. The 2022 ConvNeXt study reported that moving to 7 by 7 depthwise kernels raised its model's ImageNet accuracy from 79.9% to 80.6% at roughly constant computation, with no further gain beyond 7 by 7, and its authors compared depthwise convolution to the per-channel weighted sum in self-attention. That framing, separate operations for spatial mixing and channel mixing, now appears in both convolutional and transformer-style designs. Open problems include making depthwise layers efficient on accelerators built for dense matrix multiplication, choosing kernel sizes and expansion ratios for each layer automatically, and deciding when large-kernel depthwise convolutions or attention give the better accuracy for a given hardware budget. Each new generation of mobile and edge hardware changes those trade-offs, so published results apply to the devices and runtimes they were measured on.

āļāļēāļĢāļ™āļģāđ„āļ›āļ›āļāļīāļšāļąāļ•āļī

āļ—āļģāđ„āļĄāļĄāļąāļ™āļ–āļķāļ‡āļŠāļģāļ„āļąāļ

  • āļ•āđ‰āļ™āļ—āļļāļ™āđāļĨāļ°āļ‡āļšāļ›āļĢāļ°āļĄāļēāļ“. āļāļēāļĢāļ•āļąāļ”āļŠāļīāļ™āđƒāļˆāļ”āđ‰āļēāļ™āļŠāļ–āļēāļ›āļąāļ•āļĒāļāļĢāļĢāļĄāļ‚āļąāļšāđ€āļ„āļĨāļ·āđˆāļ­āļ™āļ›āļĢāļ°āļŠāļīāļ—āļ˜āļīāļ āļēāļžāđāļĨāļ°āļ•āđ‰āļ™āļ—āļļāļ™āļāļēāļĢāļ”āļģāđ€āļ™āļīāļ™āļ‡āļēāļ™āđ€āļ›āđ‡āļ™āđ€āļ§āļĨāļēāļŦāļĨāļēāļĒāļ›āļĩ
  • āļāļēāļĢāļ•āļąāļ”āļŠāļīāļ™āđƒāļˆāļ—āļĩāđˆāļŠāļąāļ”āđ€āļˆāļ™āļĒāļīāđˆāļ‡āļ‚āļķāđ‰āļ™. āļāļēāļĢāļĻāļķāļāļĐāļēāļ”āđ‰āļēāļ™āđ€āļ—āļ„āļ™āļīāļ„āļŠāđˆāļ§āļĒāđƒāļŦāđ‰āļ—āļĩāļĄāđ€āļĨāļ·āļ­āļāļāļĨāļļāđˆāļĄāļ—āļĩāđˆāđ€āļŦāļĄāļēāļ°āļŠāļĄ āđ„āļĄāđˆāđƒāļŠāđˆāđāļ„āđˆāļāļĨāļļāđˆāļĄāđƒāļŦāļĄāđˆāļĨāđˆāļēāļŠāļļāļ”
  • āļāļēāļĢāļ„āļ§āļšāļ„āļļāļĄāļ„āļļāļ“āļ āļēāļž. āļ•āļąāļ§āđ€āļĨāļ·āļ­āļāļ—āļēāļ‡āļ§āļīāļĻāļ§āļāļĢāļĢāļĄāļ—āļĩāđˆāļ”āļĩāļāļ§āđˆāļēāļˆāļ°āļŠāđˆāļ§āļĒāļĨāļ”āđ€āļŦāļ•āļļāļāļēāļĢāļ“āđŒāļ”āđ‰āļēāļ™āļ„āļ§āļēāļĄāļ™āđˆāļēāđ€āļŠāļ·āđˆāļ­āļ–āļ·āļ­āđƒāļ™āļāļēāļĢāļœāļĨāļīāļ•

āļĢāļ°āļ§āļąāļ‡

  • āļāļēāļĢāđ€āļžāļīāđˆāļĄāļ›āļĢāļ°āļŠāļīāļ—āļ˜āļīāļ āļēāļžāđ€āļāļ“āļ‘āđŒāļĄāļēāļ•āļĢāļāļēāļ™āļŦāļ™āļķāđˆāļ‡āļĢāļēāļĒāļāļēāļĢāļŠāļēāļĄāļēāļĢāļ–āļ‹āđˆāļ­āļ™āļˆāļļāļ”āļ­āđˆāļ­āļ™āļ‚āļ­āļ‡āļĢāļ°āļšāļšāđƒāļ™āļ§āļ‡āļāļ§āđ‰āļēāļ‡āđ„āļ”āđ‰
  • āļ•āđ‰āļ™āļ—āļļāļ™āđ‚āļ„āļĢāļ‡āļŠāļĢāđ‰āļēāļ‡āļžāļ·āđ‰āļ™āļāļēāļ™āđāļĨāļ°āļāļēāļĢāļšāļģāļĢāļļāļ‡āļĢāļąāļāļĐāļēāļĄāļąāļāļ–āļđāļāļ›āļĢāļ°āđ€āļĄāļīāļ™āļ•āđˆāļģāđ„āļ›
  • āļŠāđˆāļ­āļ‡āļ§āđˆāļēāļ‡āļ”āđ‰āļēāļ™āļ„āļ§āļēāļĄāļ›āļĨāļ­āļ”āļ āļąāļĒāđāļĨāļ°āļ„āļ§āļēāļĄāļŠāļēāļĄāļēāļĢāļ–āđƒāļ™āļāļēāļĢāļŠāļąāļ‡āđ€āļāļ•āļŠāļēāļĄāļēāļĢāļ–āđ€āļžāļīāđˆāļĄāļ‚āļķāđ‰āļ™āđ„āļ”āđ‰āđ€āļĄāļ·āđˆāļ­āļĢāļ°āļšāļšāļĄāļĩāļ„āļ§āļēāļĄāļ‹āļąāļšāļ‹āđ‰āļ­āļ™āļĄāļēāļāļ‚āļķāđ‰āļ™

āļ‚āļąāđ‰āļ™āļ•āļ­āļ™āļ•āđˆāļ­āđ„āļ›

  1. āļāļģāļŦāļ™āļ”āđ€āļ›āđ‰āļēāļŦāļĄāļēāļĒāđ€āļ§āļĨāļēāđāļāļ‡ āļ„āļļāļ“āļ āļēāļž āđāļĨāļ°āļ•āđ‰āļ™āļ—āļļāļ™āļāđˆāļ­āļ™āļ™āļģāđ„āļ›āđƒāļŠāđ‰āļ‡āļēāļ™
  2. āđ€āļāļ“āļ‘āđŒāļĄāļēāļ•āļĢāļāļēāļ™āļ āļēāļĒāđƒāļ•āđ‰āļŠāļ āļēāļ§āļ°āđ‚āļŦāļĨāļ”āđāļĨāļ°āļ‚āđ‰āļ­āļĄāļđāļĨāļˆāļĢāļīāļ‡
  3. āļāļēāļĢāļ•āļĢāļ§āļˆāļŠāļ­āļšāđ€āļ„āļĢāļ·āđˆāļ­āļ‡āļĄāļ·āļ­āđ€āļžāļ·āđˆāļ­āļŦāļēāļ‚āđ‰āļ­āļœāļīāļ”āļžāļĨāļēāļ” āļāļēāļĢāđ€āļšāļĩāđˆāļĒāļ‡āđ€āļšāļ™ āđāļĨāļ°āļœāļĨāļāļĢāļ°āļ—āļšāļ•āđˆāļ­āļœāļđāđ‰āđƒāļŠāđ‰
  4. āđ€āļ•āļĢāļĩāļĒāļĄāđ€āļŠāđ‰āļ™āļ—āļēāļ‡āļāļēāļĢāļĒāđ‰āļ­āļ™āļāļĨāļąāļšāđāļĨāļ°āļāļēāļĢāļ•āļ­āļšāļŠāļ™āļ­āļ‡āļ•āđˆāļ­āđ€āļŦāļ•āļļāļāļēāļĢāļ“āđŒāļāđˆāļ­āļ™āļ›āļĢāļąāļšāļ‚āļ™āļēāļ”

āļ—āļĩāđˆāļĄāļēāđāļĨāļ°āļ­āđˆāļēāļ™āđ€āļžāļīāđˆāļĄāđ€āļ•āļīāļĄ

  1. arXivMobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
  2. arXivXception: Deep Learning with Depthwise Separable Convolutions
  3. arXivMobileNetV2: Inverted Residuals and Linear Bottlenecks
  4. arXivShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
  5. arXivA ConvNet for the 2020s
  6. PyTorch documentationtorch.nn.Conv2d

āļŠāļģāļĢāļ§āļˆāļ•āđˆāļ­āđ„āļ›

āļˆāļ”āļŦāļĄāļēāļĒāļ‚āđˆāļēāļ§āļŸāļĢāļĩ

āļĢāļąāļšāļŠāļĢāļļāļ› AI āļĢāļēāļĒāļ§āļąāļ™

āđ€āļĢāļ·āđˆāļ­āļ‡āļĢāļēāļ§ AI āļ—āļĩāđˆāļ•āļĢāļ§āļˆāļŠāļ­āļšāđāļĨāđ‰āļ§ 3 āđ€āļĢāļ·āđˆāļ­āļ‡āļ—āļļāļāļ§āļąāļ™āļ—āļģāļ‡āļēāļ™ āđ€āļŠāđ‰āļē, āđ€āļ‚āļĩāļĒāļ™āđ€āļ›āđ‡āļ™āļ āļēāļĐāļēāļ­āļąāļ‡āļāļĪāļĐāļ˜āļĢāļĢāļĄāļ”āļē āļŸāļĢāļĩāļ•āļĨāļ­āļ”āđ„āļ› āđ„āļĄāđˆāļĄāļĩāđ‚āļ†āļĐāļ“āļē

āļ­āļĩāđ€āļĄāļĨāļŦāļ™āļķāđˆāļ‡āļ‰āļšāļąāļšāļ—āļļāļāļ§āļąāļ™āļ—āļģāļ‡āļēāļ™ āļĒāļāđ€āļĨāļīāļāļāļēāļĢāļŠāļĄāļąāļ„āļĢāđƒāļ™āļ„āļĨāļīāļāđ€āļ”āļĩāļĒāļ§ āđ€āļĢāļēāđ„āļĄāđˆāđ€āļ„āļĒāļ‚āļēāļĒāļŦāļĢāļ·āļ­āđāļŠāļĢāđŒāļ—āļĩāđˆāļ­āļĒāļđāđˆāļ­āļĩāđ€āļĄāļĨāļ‚āļ­āļ‡āļ„āļļāļ“

āļ—āļ”āļŠāļ­āļšāļ•āļąāļ§āđ€āļ­āļ‡

Take the Depthwise Separable Convolutions quiz

āļ‚āđ‰āļ­āđ€āļŠāļ™āļ­āđāļ™āļ°āļ—āļąāļ™āļ—āļĩāļŠāļģāļŦāļĢāļąāļšāļ—āļļāļāļ„āļģāļ•āļ­āļš āđāļĨāļ°āđƒāļšāļĢāļąāļšāļĢāļ­āļ‡āļ—āļĩāđˆāļŠāļēāļĄāļēāļĢāļ–āđāļŠāļĢāđŒāđ„āļ”āđ‰āļžāļĢāđ‰āļ­āļĄ ID āļ—āļĩāđˆāļ•āļĢāļ§āļˆāļŠāļ­āļšāđ„āļ”āđ‰āđ€āļĄāļ·āđˆāļ­āļ„āļļāļ“āļœāđˆāļēāļ™āļŦāļĨāļąāļāļŠāļđāļ•āļĢ

āđ€āļĢāļīāđˆāļĄāđāļšāļšāļ—āļ”āļŠāļ­āļš

āļŠāļ™āļąāļšāļŠāļ™āļļāļ™āļāļēāļĢāļĻāļķāļāļĐāļē AI āļŸāļĢāļĩ AI Understanding āđ€āļ›āđ‡āļ™āļ­āļ‡āļ„āđŒāļāļĢāđ„āļĄāđˆāđāļŠāļ§āļ‡āļŦāļēāļœāļĨāļāļģāđ„āļĢ 501(c)(3) — āđ„āļĄāđˆāļĄāļĩāđ‚āļ†āļĐāļ“āļē āđ„āļĄāđˆāļĄāļĩāļāļģāđāļžāļ‡āđ€āļ‡āļīāļ™, āļ•āļĨāļ­āļ”āđ„āļ› āļšāļĢāļīāļˆāļēāļ„

āļ„āļģāļ–āļēāļĄāļ—āļĩāđˆāļžāļšāļšāđˆāļ­āļĒ

What is Depthwise Separable Convolutions?

A depthwise separable convolution splits an ordinary convolution layer into two cheaper steps: a depthwise step that filters each channel on its own, and a 1 by 1 pointwise step that mixes channels. With 3 by 3 kernels it needs roughly 8 to 9 times less computation, which is why it underpins mobile vision networks such as MobileNet and Xception.

āļŠāļ­āļ‡āļ‚āļąāđ‰āļ™āļ•āļ­āļ™āļ—āļĩāđˆāļāļēāļĢāļšāļīāļ”āđāļšāļšāđāļĒāļāļŠāđˆāļ§āļ™āđ€āļŠāļīāļ‡āļĨāļķāļāļˆāļ°āđāļĒāļāļāļēāļĢāļšāļīāļ”āđāļšāļšāļĄāļēāļ•āļĢāļāļēāļ™āļ­āļ­āļāđ€āļ›āđ‡āļ™āļ­āļ°āđ„āļĢ?

āļ‚āļąāđ‰āļ™āļ•āļ­āļ™āđ€āļŠāļīāļ‡āļĨāļķāļāļˆāļ°āļāļĢāļ­āļ‡āđāļ•āđˆāļĨāļ°āļŠāđˆāļ­āļ‡āđ€āļŠāļīāļ‡āļžāļ·āđ‰āļ™āļ—āļĩāđˆāļ”āđ‰āļ§āļĒāļ•āļąāļ§āļĄāļąāļ™āđ€āļ­āļ‡ āļˆāļēāļāļ™āļąāđ‰āļ™āļ‚āļąāđ‰āļ™āļ•āļ­āļ™ 1x1 āđāļšāļš pointwise āļˆāļ°āļĢāļ§āļĄāļ‚āđ‰āļ­āļĄāļđāļĨāļ‚āđ‰āļēāļĄāļŠāđˆāļ­āļ‡āļŠāļąāļāļāļēāļ“

āđƒāļ™āļ‚āļąāđ‰āļ™āļ•āļ­āļ™āđ€āļŠāļīāļ‡āļĨāļķāļ āļŠāđˆāļ­āļ‡āļŠāļąāļāļāļēāļ“āđ€āļ‚āđ‰āļēāđ„āļ”āđ‰āļĢāļąāļšāļāļēāļĢāļ›āļāļīāļšāļąāļ•āļīāļ­āļĒāđˆāļēāļ‡āđ„āļĢ?

āļāļēāļĢāļšāļīāļ”āđāļšāļšāđ€āļŠāļīāļ‡āļĨāļķāļāļˆāļ°āđƒāļŠāđ‰āļ•āļąāļ§āļāļĢāļ­āļ‡āđ€āļŠāļīāļ‡āļžāļ·āđ‰āļ™āļ—āļĩāđˆāđāļĒāļāļ•āđˆāļēāļ‡āļŦāļēāļāļāļąāļšāđāļ•āđˆāļĨāļ°āļŠāđˆāļ­āļ‡āļŠāļąāļāļāļēāļ“āđ€āļ‚āđ‰āļēāđ‚āļ”āļĒāđ„āļĄāđˆāļĄāļĩāļāļēāļĢāļœāļŠāļĄāļŠāđˆāļ­āļ‡āļŠāļąāļāļāļēāļ“ āļ‹āļķāđˆāļ‡āļ—āļģāđƒāļŦāđ‰āļĢāļēāļ„āļēāļ–āļđāļ

For many output channels, what operation-count reduction does the guide associate with a 3×3 depthwise separable convolution?

āļŠāļģāļŦāļĢāļąāļšāđ€āļ„āļ­āļĢāđŒāđ€āļ™āļĨ 3x3 āļ­āļąāļ•āļĢāļēāļŠāđˆāļ§āļ™āļāļēāļĢāļ›āļĢāļ°āļŦāļĒāļąāļ”āļˆāļ°āđ€āļ‚āđ‰āļēāđƒāļāļĨāđ‰ 1/9 āđ€āļĄāļ·āđˆāļ­āļˆāļģāļ™āļ§āļ™āļŠāđˆāļ­āļ‡āļŠāļąāļāļāļēāļ“āđ€āļ­āļēāļ—āđŒāļžāļļāļ•āļĄāļĩāļ‚āļ™āļēāļ”āđƒāļŦāļāđˆ āļ—āļģāđƒāļŦāđ‰āļāļēāļĢāļ—āļģāļ‡āļēāļ™āļ™āđ‰āļ­āļĒāļĨāļ‡āļ›āļĢāļ°āļĄāļēāļ“ 8 āļ–āļķāļ‡ 9 āđ€āļ—āđˆāļē

āļšāļ—āļšāļēāļ—āļ‚āļ­āļ‡āļāļēāļĢāļšāļīāļ”āđāļšāļš pointwise (1x1) āđƒāļ™āļāļēāļĢāļ­āļ­āļāđāļšāļšāļ™āļĩāđ‰āļ„āļ·āļ­āļ­āļ°āđ„āļĢ?

āļāļēāļĢāļšāļīāļ”āļ•āļēāļĄāļˆāļļāļ”āļ‚āļ™āļēāļ” 1x1 āļˆāļ°āļœāļŠāļĄāļŠāđˆāļ­āļ‡āļŠāļąāļāļāļēāļ“āđƒāļ™āļ—āļļāļāļžāļīāļāđ€āļ‹āļĨ āļ‹āļķāđˆāļ‡āļ‚āļąāđ‰āļ™āļ•āļ­āļ™āđ€āļŠāļīāļ‡āļĨāļķāļāļˆāļ‡āđƒāļˆāļŦāļĨāļĩāļāđ€āļĨāļĩāđˆāļĒāļ‡āļāļēāļĢāļ—āļģ

āļŠāļ–āļēāļ›āļąāļ•āļĒāļāļĢāļĢāļĄāļ—āļĩāđˆāļĄāļĩāļŠāļ·āđˆāļ­āđ€āļŠāļĩāļĒāļ‡āđƒāļ”āļ—āļĩāđˆāđ„āļ”āđ‰āļĢāļąāļšāļ„āļ§āļēāļĄāļ™āļīāļĒāļĄāđƒāļ™āļāļēāļĢāđ‚āļ™āđ‰āļĄāļ™āđ‰āļēāļ§āđƒāļˆāđāļšāļšāđāļĒāļāļŠāđˆāļ§āļ™āđ€āļŠāļīāļ‡āļĨāļķāļāļŠāļģāļŦāļĢāļąāļšāļ­āļļāļ›āļāļĢāļ“āđŒāđ€āļ„āļĨāļ·āđˆāļ­āļ™āļ—āļĩāđˆ

MobileNet āļ–āļđāļāļŠāļĢāđ‰āļēāļ‡āļ‚āļķāđ‰āļ™āđ‚āļ”āļĒāđƒāļŠāđ‰āļāļēāļĢāđ‚āļ™āđ‰āļĄāļ™āđ‰āļēāļ§āđƒāļˆāđāļšāļšāđāļĒāļāļŠāđˆāļ§āļ™āđ€āļŠāļīāļ‡āļĨāļķāļāđ‚āļ”āļĒāđ€āļ‰āļžāļēāļ°āđ€āļžāļ·āđˆāļ­āđƒāļŦāđ‰āļŠāļēāļĄāļēāļĢāļ–āļ­āļ™āļļāļĄāļēāļ™āđ„āļ”āđ‰āļ­āļĒāđˆāļēāļ‡āļĄāļĩāļ›āļĢāļ°āļŠāļīāļ—āļ˜āļīāļ āļēāļžāļšāļ™āđ‚āļ—āļĢāļĻāļąāļžāļ—āđŒ

āđ€āļĢāļĩāļĒāļ™āļĢāļđāđ‰āļ•āđˆāļ­āđ„āļ›

āļ„āļģāđāļ™āļ°āļ™āļģāļ—āļĩāđˆāđ€āļāļĩāđˆāļĒāļ§āļ‚āđ‰āļ­āļ‡

āļ„āļģāđāļ™āļ°āļ™āļģāđ€āļžāļīāđˆāļĄāđ€āļ•āļīāļĄāļ—āļĩāđˆāđ€āļĨāļ·āļ­āļāļŠāļģāļŦāļĢāļąāļšāļŦāļąāļ§āļ‚āđ‰āļ­āļ™āļĩāđ‰

āļ•āđˆāļ­āđ„āļ›āļ„āļģāđāļ™āļ°āļ™āļģāļ•āđˆāļ­āđ„āļ›

āļāļēāļĢāđ‚āļ™āđ‰āļĄāļ™āđ‰āļēāļ§āđƒāļˆāļ—āļĩāđˆāđ€āļ›āļĨāļĩāđˆāļĒāļ™āļĢāļđāļ›āđ„āļ”āđ‰

āļ§āļīāļŠāļ§āļĨāđ€āļ­āđ„āļ­

āļĢāļąāļšāđƒāļšāļĢāļąāļšāļĢāļ­āļ‡ AI āļŸāļĢāļĩāļŦāļĨāļąāļāļŠāļđāļ•āļĢāđāļĨāļ°āļāļēāļĢāļŠāļ­āļšāļŠāļąāđ‰āļ™ āđ† āļŸāļĢāļĩ āđ„āļĄāđˆāļĄāļĩāļ„āđˆāļēāđƒāļŠāđ‰āļˆāđˆāļēāļĒ āđ„āļĄāđˆāļĄāļĩāļšāļąāļ•āļĢāđ€āļ„āļĢāļ”āļīāļ• āļ›āļĢāļ°āļĄāļēāļ“ 2.5 āļŠāļąāđˆāļ§āđ‚āļĄāļ‡āđ€āļĢāļīāđˆāļĄāļ•āđ‰āļ™āļŸāļĢāļĩ →