Skip to content

v2.2.0
Compare
Choose a tag to compare
@milakov milakov released this 05 Jul 18:55
· 54 commits to master since this release
v2.2.0
454b4a3
  • Convolutional layer
    -- strides added
    -- w/out bias option added
  • check_gradient command added
  • Imagenet: reproduced ResNet50 result (7.5% Top5 single crop)
  • Average subsampling layer allows specifying output size instead of subsampling window sizes
  • Added profiling to CUDA backend
  • Max subsampling layer:
    -- round_up mode added
    -- Strides added
  • Step learning rate decay policy added
  • Added update_bn_weights action (but calculating mean and invsigma during training works well)
  • Spatial Transformer:
    -- affine_grid_generator_layer added
    -- linear_sampler layer added
  • Utilizing cudnnFindConvolution*AlgorithmEx functions to get maximum perf (cuDNN v5 is required for that)
  • Added strides to sparse convolution layer
Assets 2
Loading