7 Commits

Author	SHA1	Message	Date
youben11	7901d8868c	fix: adhere to ONNX spec of kernel_shape ... ONNX spec: "kernel_shape : list of ints The shape of the convolution kernel. If not present, should be inferred from input W." We were taking the number of input/output feature maps into account, which we realized we should not.	2022-10-05 14:55:54 +01:00
youben11	0aadb4ac43	feat: support grouped conv2D	2022-08-16 16:28:37 +01:00
Umut	8a60a979cb	chore: remove manually set uint8 dtypes in tests as it's done automatically	2022-06-22 11:03:48 +03:00
Umut	ffe26aadcb	refactor: move configuration and artifacts to compile and trace methods	2022-04-29 11:10:14 +03:00
youben11	840a9c2c20	feat: support tracing/eval of ONNX Conv ... - 1D, 2D, and 3D convolutions - conversion to MLIR is supported only for 2D convolution - not full support yet: still limitations on group and other params	2022-04-27 08:18:14 +01:00
youben11	824e034084	refactor: add concrete.onnx mod with previous conv2d ... the module is meant to contain machine learning operations as defined by ONNX	2022-04-13 13:10:53 +01:00
Umut	c45b9ffa43	feat: rewrite tests	2022-04-08 12:09:44 +03:00