Margaret Qian efe662fe66 [Relay][Pass] Add a relay pass to extract fake quantized ops (#10089) ...

* add relay pass to collect fake quantized ops

* add more tests

* more tests

* lint

* lint

* remove unused imports

* update comment

* lint

* reuse SubgraphExtractor and update test assertions

* remove print

* lint

* remove unneeded comment

Co-authored-by: Margaret Qian <mqian@octoml.ai>

2022-02-01 20:57:45 -08:00

..

__init__.py

[Autoscheduler] Add sparse conv2d(1*1) support for auto_scheduler (#8065)

2021-05-19 18:52:56 +08:00

_ffi_api.py

[Refactor][Relay] Refactor Relay Python to use new FFI (#5077)

2020-03-17 08:33:10 -07:00

analysis.py

[Relay][Pass] Add a relay pass to extract fake quantized ops (#10089)

2022-02-01 20:57:45 -08:00

annotated_regions.py

Fixes for using Python APIs from Rust. (#7085)

2021-03-04 10:43:14 -08:00

call_graph.py

Fixes for using Python APIs from Rust. (#7085)

2021-03-04 10:43:14 -08:00

count_layers.py

[Relay] A set of utilities that allows a model to be run efficiently on tensorcores. (#6748)

2020-10-26 19:37:05 -04:00

feature.py

fix py files (#8194)

2021-06-04 23:22:46 +01:00

sparse_conv2d.py

[TOPI] [Relay] Sparse Conv2d Implementation for 3x3 kernels (#8605)

2021-08-27 09:18:34 +08:00

sparse_dense.py

[Refactor] Rename asnumpy -> numpy in NDArray (#8083)

2021-05-21 08:32:27 -04:00