Now we are announcing v1.0.0a3. Thanks for all great contributors! This release includes the following changes from v1.0.0a2:

Bug fix

• Convolutional layer with padding::same mode doesn't work #332 fixed by @nyanp
• Segmentation fault at MinGW build #203 #281 fixed by @nyanp
• NNPACK backend doesn't work #398 fixed by @azsane

Improvements

• Remove compiler warnings & improve CMakeLists #387 by @beru
• Improve memory consumption #410 by @beru
• Improve unit tests #408 by @Randl
• Subtle speed optimization #419 by @beru
• Refactor serialization type & size type #407, #422 by @Randl and @edgarriba
• Improve compilation time by splitting serialiation/deserialization #421 by @beru

Docs&Comments

• Add comments to layer class #424 by @edgarriba
• Fix typo in comments #404 by @MikalaiDrabovich

Toward v1.0.0

The first version of tensor is merged into tiny-dnn (#411 #417 #418 by @pansk @Randl and @edgarriba). It isn't integrated with tiny-dnn layers yet, but it's the starting point of the GPU tiny-dnn.

Bug Fixes

• Fix SEGV errors on AVX Optimized code (#353) by @nyanp
• Fix compiler error on msvc2013 (#320) by @nyanp
• Fix AVX backend slowdown on convolutional layer (#322) by @nyanp
• Fix throwing error when we load weights manually (#330) by @nyanp
• Fix returning infinity in tan_h (#347) by @nyanp
• Fix portability issues on serialization (#377) by @nyanp

Features

• Provides compile option to disable serialization support to speedup compilation time (#316) by @nyanp
• Adds set_trainable method to freeze layers (#346) by @nyanp
• Adds power layer to caffe converter by @goranrauker
• double precision support (#332) by @nyanp
• Provides pad_type and non-square input to pooling layers (#374) by @nyanp
• Adds public predict method for vector of tensors (#396) by @reunanen
• Adds Auto engine selection (#339) by @edgarriba
• Adds basic image utilities, and remove OpenCV dependencies (#337) by @nyanp

Others

• Sync with latest NNPACK by @azsane
• Improves compiler warnings around type-cast by @pansk @reunanen @edgarriba
• Improves CMakelist by @syoyo @edgarriba @beru
• Replaces picotest with gtest by @Randl
• Adds "layer catalogue" into official documentation by @nyanp
• Adds tests for GPU environment by @Randl
• Adds cpplint.py by @edgarriba @Randl
• Adds a document for building iOS app by @wangyida
• Adds coverall checking by @edgarriba
• Adds CI builds for Win32 by @nyanp
• Updates & improves readme by @edgarriba @zhangqianhui

🎉 This release contains a major refactoring & many bugfixes. Thanks a lot for all great contributors! 🎉

This release is alpha version. We need more helps and feedbacks toward v1.0.0. Please submit your bug-report at Github issue. Many thanks :)

• Major updates

  • Merge successful results from GSoC 2016
    • OpenCL & GPU backends by @edgarriba
    • Quantization by @wangyida

  These features are still experimental, so PRs and bug reports are very welcome!

  • Model serialization by @nyanp

• Minor bug fix

  • Memory errors in cifar-10 example #295 #300 by @edgarriba
  • Fix max-pooling layer #271 by @nyanp
  • Fix concat-layer #301 by @Jiaolong
  • Suppress compiler warnings #297 by @syoyo

• Other

  • A nice project logo by @KonfrareAlbert
  • Launch official documents at http://tiny-dnn.readthedocs.io/

some APIs are changed from v0.1.1 .

• changed its namespace from tiny_cnn to tiny_dnn
• changed API header from tiny_cnn.h to tiny_dnn.h

This release contains following improvements:

• New Layers
  • Batch Normalization
  • Deconvolution/Unpooling (@wangyida)
  • Power
  • Slice
• New Loss Functions
  • Absolute mean/Absolute mean with eps (@H4kor)
• Minor Bug Fix
  • Compile error on MSVC2013 #218 #231
  • Correct the definition of MSE #232
  • Fix linker error due to duplicate symbols
  • Fix handling non-square input data in caffemodel #227
  • Fix data race in network::test #185

Thank you very much for all comitters for this release!

This release contains a major refactoring around fundamental architecture of tiny-cnn and fixes many problems. We had the help of 20 comitters for this release. Thanks!

• Now we can handle non-sequential model as network<graph> #108
  #153
• Catch up the latest format of caffe's proto #162
• Improve the default behaviour of re-init weight #136
• Add more tests and documents #73
• Remove dependency of OpenCV in MNIST example

Some API have changed from the previous release. see change list