Commits · 09f7b5b05424ef671077866b57097c084ac0d02a · Max Ehrlich / cdcnn

07 Dec, 2018 2 commits
- Add relu accuracy for MNIST and CIFAR10 · 09f7b5b0
  Max Ehrlich authored Dec 07, 2018
  
  09f7b5b0
- Simplify relu blocks plot script · bd20f96b
  Max Ehrlich authored Dec 07, 2018
  
  bd20f96b
06 Dec, 2018 9 commits
- Use apxrelu from the layers package · f3bf1bec
  Max Ehrlich authored Dec 06, 2018
  
  f3bf1bec
- Add relu accuracy experiment · e249d6e7
  Max Ehrlich authored Dec 06, 2018
  
  e249d6e7
- Add relu layer using direct approximation · df707d83
  Max Ehrlich authored Dec 06, 2018
  
  df707d83
- Slight change to relu blocks output data format · 46fb2b06
  Max Ehrlich authored Dec 06, 2018
  
  46fb2b06
- Formatting changes for the relu blocks plot · 71631865
  Max Ehrlich authored Dec 06, 2018
  
  71631865
- Corrected relu blocks results · de6a8362
  Max Ehrlich authored Dec 06, 2018
  
  de6a8362
- Minor fixes to relu blocks test · 4851be26
  Max Ehrlich authored Dec 06, 2018
  
  4851be26
- Preliminary plot for relu_blocks error · 30d1c887
  Max Ehrlich authored Dec 06, 2018
  
  30d1c887
- Add relu blocks result · 409b93b9
  Max Ehrlich authored Dec 06, 2018
  
  409b93b9
05 Dec, 2018 10 commits
- Simple training experiment · 65a729a5
  Max Ehrlich authored Dec 05, 2018
  
  65a729a5
- Batch norm training mode first attempt · cc5094a1
  Max Ehrlich authored Dec 05, 2018
  
  cc5094a1
- Remove double import · 79824871
  Max Ehrlich authored Dec 05, 2018
  
  79824871
- Make sure conv weight is registered as a param · b36dfadd
  Max Ehrlich authored Dec 05, 2018
  
  b36dfadd
- Dont retain the graph, it wastes memory · 81d5c18c
  Max Ehrlich authored Dec 05, 2018
  
  81d5c18c
- Fix shape broadcasting bug · a99367a8
  Max Ehrlich authored Dec 05, 2018
  
  a99367a8
- Remove scipy · 90171997
  Max Ehrlich authored Dec 05, 2018
  
  90171997
- Finish model conversion results · fcdefba1
  Max Ehrlich authored Dec 05, 2018
  
  fcdefba1
- Ignore latex generated files · 4771e4c6
  Max Ehrlich authored Dec 05, 2018
  
  4771e4c6
- Add paper draft · 07079fdb
  Max Ehrlich authored Dec 05, 2018
  
  07079fdb
04 Dec, 2018 15 commits
- Faster processing using batched operations · 3fb46936
  Max Ehrlich authored Dec 04, 2018
  
  3fb46936
- Add relu blockwise experiment · 66175009
  Max Ehrlich authored Dec 04, 2018
  
  66175009
- Fix decoding bug · f5792788
  Max Ehrlich authored Dec 04, 2018
  
  f5792788
- Print dataset name · 35b472e4
  Max Ehrlich authored Dec 04, 2018
  
  35b472e4
- Make sure to batch norm after downsampling convolution · b0a76158
  Max Ehrlich authored Dec 04, 2018
  
  b0a76158
- Allow exploded convolutions to be precomputed for faster testing · b19163d7
  Max Ehrlich authored Dec 04, 2018
  
  b19163d7
- Correct handling of blocks with different input and output channels · 42ad5fb3
  Max Ehrlich authored Dec 04, 2018
  
  42ad5fb3
- Fix dataset paths · f70d43ed
  Max Ehrlich authored Dec 04, 2018
  
  f70d43ed
- For number format in printing progress · 3e432454
  Max Ehrlich authored Dec 04, 2018
  
  3e432454
- Fix report printing · 70e704fd
  Max Ehrlich authored Dec 04, 2018
  
  70e704fd
- Fix label datatype · 5ab3c802
  Max Ehrlich authored Dec 04, 2018
  
  5ab3c802
- Modify model code to be device independent · 5726be9f
  Max Ehrlich authored Dec 04, 2018
  
  5726be9f
- Add model conversion experiment code · 84dd7d06
  Max Ehrlich authored Dec 04, 2018
  
  84dd7d06
- Add dataset information · 1009394f
  Max Ehrlich authored Dec 04, 2018
  
  1009394f
- Fix bugs in jpeg data loading · e29753b4
  Max Ehrlich authored Dec 04, 2018
  
  e29753b4
03 Dec, 2018 4 commits
- Add jpeg loading tools · 3b8e93f7
  Max Ehrlich authored Dec 03, 2018
  
  3b8e93f7
- Top level init.py · ee122b95
  Max Ehrlich authored Dec 03, 2018
  
  ee122b95
- Add dataset conversion and loading tools · cbde3c94
  Max Ehrlich authored Dec 03, 2018
  
  cbde3c94
- Allow variable number of input channels · b59d8c91
  Max Ehrlich authored Dec 03, 2018
  
  b59d8c91