GitXplorerGitXplorer
r

tensorflow-resnet

public
1661 stars
627 forks
38 issues

Commits

List of commits on branch master.
Unverified
ccb9cc8cc2cc7021c67e7df4a70f96faab9553c5

Update readme to say how old this code is.

rry committed 7 years ago
Unverified
c87a7e2c6ed62c968bf89198380f531bf0edc10d

update config

rry committed 9 years ago
Unverified
4acf7ab8e099c2141e0e5e858a955bcff249e17e

add API for using calling inference_small with a config

rry committed 9 years ago
Unverified
aad01948027727a418cd0630f14a3a742f6ff385

use Config

rry committed 9 years ago
Unverified
76d0b5cc34f586a0d510f6f079add9fcfc5cce49

add max_steps flag

rry committed 9 years ago
Unverified
a2f1af991466e64c00b5d753c51370b39ddc32b8

Run validation periodically during training

rry committed 9 years ago

README

The README file for this repository.

This code is very old and doesn't run on modern TensorFlow. Indeed, TF now includes a resnet model in its core library: https://github.com/tensorflow/tensorflow/blob/master/tensorflow/contrib/slim/python/slim/nets/resnet_v1.py

Also checkout my new ML project at http://propelml.org/

ResNet in TensorFlow

Implemenation of Deep Residual Learning for Image Recognition. Includes a tool to use He et al's published trained Caffe weights in TensorFlow.

MIT license. Contributions welcome.

Goals

  • Be able to use the pre-trained model's that Kaiming He has provided for Caffe. The convert.py will convert the weights for use with TensorFlow.

  • Implemented in the style of Inception not using any classes and making heavy use of variable scope. It should be easily usable in other models.

  • Foundation to experiment with changes to ResNet like stochastic depth, shared weights at each scale, and 1D convolutions for audio. (Not yet implemented.)

  • ResNet is fully convolutional and the implementation should allow inputs to be any size.

  • Be able to train out of the box on CIFAR-10, 100, and ImageNet. (Implementation incomplete)

Pretrained Model

To convert the published Caffe pretrained model, run convert.py. However Caffe is annoying to install so I'm providing a download of the output of convert.py:

tensorflow-resnet-pretrained-20160509.tar.gz.torrent 464M

Notes

  • This code depends on TensorFlow git commit cf7ce8 or later because ResNet needs 1x1 convolutions with stride 2. TF 0.8 is not new enough.

  • The convert.py script checks that activations are similiar to the caffe version but it's not exactly the same. This is probably due to differences between how TF and Caffe handle padding. Also preprocessing is done with color-channel means instead of pixel-wise means.