Skip to content

Releases: 1adrianb/pytorch-estimate-flops

v0.4.1 released

28 Apr 21:33
bdc19ad
Compare
Choose a tag to compare

[Add] Added support for FX based estimation for pytorch 1.8 and newer, jit based approach is deprecated.
[Fix] Fixed 2 issues with the jit based estimator (@senysenyseny16)

v0.3.5 released

11 Jan 13:18
Compare
Choose a tag to compare

[Fix] Added support for pytorch 1.8.0

v0.3.4 released

23 Dec 23:05
Compare
Choose a tag to compare

[Fix] Issue when the input is a list
[Fix] Regex problem when the tensor was on a cuda device

v0.3.0 released

24 Aug 13:34
Compare
Choose a tag to compare

[Fix] Added support for pytorch 1.6.0
[Fix] Fix ignore flag issues with pytorch 1.4.0 and newer
[Fix] Custom ops were previously ignored

v0.2.2 released

18 Jan 13:35
Compare
Choose a tag to compare

[Fix] Fixed compatibility with pytorch 1.4.0

v0.2.1 released

17 Sep 15:32
Compare
Choose a tag to compare

[Change] A detailed dictionary containing each op is now also returned
[Add] Added support for mul, global average pooling and matmul

v0.2.0 released

16 Aug 22:45
Compare
Choose a tag to compare

[Fix] Issue with ndConvs (thanks Jean!)
[Add] Added option to display the flops for each individual layer
[Add] Added option to ignore certain module types
[Add] Added option to provide custom functions for computing the OPs

Initial release

09 Feb 02:21
Compare
Choose a tag to compare

Initial release with the main structure and a few basic ops