We have released Neural Network Libraries 1.7.0! prohibit_clear flag has been added to prevent unintentional removal of inplaced variable data! We have also new examples including SPADE, data augmentation, and facial keypoint detection examples! Even more, we have added better performing models for ImageNet!

Spotlight

BugFix: prohibit_clear flag to keep inplaced data from clear_buffer

We have noticed that, in previous versions, when you inplace a variable, its persistent flag was ignored, resulting in its data unintentionally getting removed. This is a bug that can lead to computation error, so we STRONGLY suggest upgrading to the latest version!

SPADE

We have implemented SPADE, which allows users to synthesize images with semantic maps and styles! Rough drawings can now be converted to photorealistic street views or beautiful scenery!

Input	Output

Data augmentation examples

We have added examples showing how to implement data augmentation with various techniques including MixUp, CutMix, and VH-MixUp!

Image 1	Image 2	Mixup	CutMix	VH-Mixup

Refer to our new data augmentation example page for further details!

Facial-keypoint-detection inference

We have implemented inference for face alignment network (FAN)!

Result by 2D-FAN	Result by 3D-FAN

We can now easily detect facial landmarks, give it a try!

Better performance models and training scripts for ImageNet ILSVRC2012

We have updated models and training scripts for ImageNet ILSVRC2012! Configuration is easier now, and cosine annealing learning rate decay and mixup regularization have been added! Also, training and inference scripts for new models have been added, including RexNeXt50, SE-ResNet50 and SE-RexNeXt50!

Layers

• Double Backward for ChannelLast and Half Type
• RandomErase Function

Models

• Add keyword “lastfeature” to nnabla models

Utilities/Format Conversion

• Feature/20200304 support file object in save.py and load.py
• Add Unpooling support in opset greater than 9.
• Fix MaxPooling and PReLU
• FIX: Compatibility with DALI 0.18.0
• Update reamdme and Dockerfile to support dali 0.18.0
• Add NanInfTracer

Examples

• modified prototypical net examples for fewshot face identification
• FIX: Compatibility with DALI 0.18.0
• add saving nnp/checkpoint functions to metalearning
• Refactoring ESRGAN

Bug Fix/Documentation​

• Fix load_save_parameter problem by adding ios::binary
• Fix type name is not allowed.
• modified meta-learning/README.md