開放
Weights shape not validated against kernel, channels
good first issuehelp wanted
5 則留言1 個反應0 負責人
議題
開放
ConvTranspose with padding on cpu throws exception
bughelp wanted
1 則留言0 個反應0 負責人
開放
Add docs note about saving/loading models with anonymous functions
documentationhelp wanted
9 則留言1 個反應0 負責人
開放
Separate nightly CI from posted CI badge
discussiongood first issuetesting
2 則留言0 個反應0 負責人
開放
reducing invalidations
help wanted
1 則留言0 個反應0 負責人
開放
Functional equivalents missing for some layers
enhancementgood first issue
3 則留言0 個反應0 負責人
開放
More robust testing for AlphaDropout
good first issuehelp wantedtesting
6 則留言0 個反應0 負責人
開放
Overloading Flux.batch for custom eltypes
enhancementgood first issuehelp wanted
13 則留言0 個反應0 負責人
開放
Figure out consistent code style
discussionhelp wanted
9 則留言0 個反應0 負責人
開放
Benchmark optimizer latency on GPU
cudahelp wantedperformance
0 則留言0 個反應0 負責人
開放
Allow BatchNorm training on CUDA with `track_stats=false`
good first issuehelp wanted
4 則留言0 個反應0 負責人
開放
PyTorch feature parity
help wanted
94 則留言33 個反應0 負責人
開放
Shape-propagating Chain
discussionenhancementhelp wanted
8 則留言8 個反應0 負責人
開放
'cell_clip' and 'proj_clip' for Flux: LSTM
enhancementhelp wanted
1 則留言0 個反應0 負責人
開放
Optional batch dimension for convolutions
help wanted
3 則留言0 個反應0 負責人
開放
Provide aliases for unicode fields and keywords
good first issuehelp wanted
5 則留言0 個反應0 負責人
開放
Does Flux support N-dimensional convolutions, where N>3?
enhancementhelp wanted
20 則留言0 個反應0 負責人
開放
Add max/mean unpooling operations
enhancementgood first issuehelp wanted
5 則留言6 個反應0 負責人
開放
ConvRNN Cell and ConvLSTM Cell
RNNhelp wanted
5 則留言0 個反應0 負責人