15 Commits

Author	SHA1	Message	Date
jfrery	65be1b0818	feat: use signed weights in compile_torch_model	2021-12-23 11:24:02 +01:00
Umut	4e6c57766a	refactor: improve isclose used in quantization tests	2021-12-20 12:19:06 +03:00
Umut	5aad8c50ac	test: create check_array_equality fixture	2021-12-06 16:44:32 +03:00
Arthur Meyre	a0c26315ea	chore: make check_is_good_execution a fixture and fix flaky tests using it ... closes #1061	2021-12-03 17:43:11 +01:00
Arthur Meyre	c7255dfd66	feat: update compile_torch_model to return compiled quantized module ... closes #898	2021-12-03 10:32:04 +01:00
jfrery	bf70396340	fix: increase the input data range to fix error when only one weight per layer	2021-12-03 09:24:00 +01:00
jfrery	54c0bc6e87	test: disable flaky tests	2021-12-01 10:48:41 +01:00
jfrery	1625475897	feat: end-to-end compilation of a torch model	2021-11-30 11:30:13 +01:00
jfrery	dfc762c2e2	feat: add QuantizedReLU6 as a supported activation function	2021-11-26 16:55:52 +01:00
Benoit Chevallier-Mames	ec396effb2	chore: seed torch as much as possible ... closes #877	2021-11-24 09:47:37 +01:00
jfrery	aa60d8ace6	fix: test_quantized_layer	2021-11-18 19:23:27 +01:00
jfrery	a5b1d6232e	feat: add signed intergers quantization	2021-11-18 17:21:28 +01:00
Arthur Meyre	507ccd05c5	feat: static post training quantization and quantization module	2021-11-18 10:31:45 +01:00
jfrery	c978107124	feat: remove transpose from layers	2021-11-17 14:54:16 +01:00
jfrery	c5952cd09f	feat: add quantization utilities	2021-11-10 18:25:31 +01:00