BSConv Versions Save

Reference implementation for Blueprint Separable Convolutions (CVPR 2020)

v0.4.0

3 years ago

BSConv for PyTorch:
- added support for more model architectures (see bsconv.pytorch.get_model)
- added result tables and plots for ResNets, WRNs, MobileNets on CIFAR datasets
- removed script bin/bsconv_pytorch_list_architectures.py, because bsconv.pytorch.get_model is more flexible now (see the BSConv PyTorch usage readme for available architectures)

v0.3.0

3 years ago

BSConv for PyTorch:
- added ready-to-use model definitions (MobileNetV1, MobileNetV2, MobileNetsV3, ResNets and WRNs and their BSConv variants for CIFAR and ImageNet/fine-grained datasets)
- added training script for CIFAR and ImageNet/fine-grained datasets
- added class for the StanfordDogs dataset

v0.2.0

4 years ago

BSConv for PyTorch:
- removed activation and added option for normalization of PW layers in BSConv-S (issue #1) (API change)
- added option for normalization of PW layers in BSConv-U (API change)
- ensure that BSConv-S never uses more mid channels (= M') than input channels (M) and added parameter min_mid_channels (= M'_min) (API change)
- added model profiler for parameter and FLOP counting
- replacer now shows number of old and new model parameters

v0.1.0

4 years ago

first public version
BSConv for PyTorch:
- modules BSConvU and BSConvS
- replacers BSConvU_Replacer and BSConvS_Replacer