OurBigBook About$ Donate
 Sign in+ Sign up
by Ciro Santilli (@cirosantilli, 37)

ResNet variant

 ... Computer Machine learning Neural network Artificial neural network ANN model Residual neural network
 0 By others on same topic  0 Discussions  Updated 2025-05-29  +Created 1970-01-01  See my version
  • Table of contents
    • ResNet v1 vs v1.5 ResNet variant

ResNet v1 vs v1.5

 0  0 
ResNet variant
catalog.ngc.nvidia.com/orgs/nvidia/resources/resnet_50_v1_5_for_pytorch explains:
The difference between v1 and v1.5 is that, in the bottleneck blocks which requires downsampling, v1 has stride = 2 in the first 1x1 convolution, whereas v1.5 has stride = 2 in the 3x3 convolution.
This difference makes ResNet50 v1.5 slightly more accurate (~0.5% top1) than v1, but comes with a small performance drawback (~5% imgs/sec).

 Ancestors (10)

  1. Residual neural network
  2. ANN model
  3. Artificial neural network
  4. Neural network
  5. Machine learning
  6. Computer
  7. Information technology
  8. Area of technology
  9. Technology
  10.  Home

 View article source

 Discussion (0)

+ New discussion

There are no discussions about this article yet.

 Articles by others on the same topic (0)

There are currently no matching articles.
  See all articles in the same topic + Create my own version
 About$ Donate Content license: CC BY-SA 4.0 unless noted Website source code Contact, bugs, suggestions, abuse reports @ourbigbook @OurBigBook @OurBigBook