IntenseWebs/openvino
3
0 Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
Files
6d8dcb059d7c5eb4ad0a1b7006d807689f8922b4
openvino/tests/layer_tests/pytorch_tests
T
History
Piotr KrzemińskiandMaxim Vafin 6d8dcb059d [PT FE] Fix conversion for aten::quantize_per_channel (#18646) 
* Support GetAttr with packed params

* Apply suggestions from code review

* [PT FE] Add quantized types as normal types to decoder

* [PT FE] Add decoder dequantize, add dtypes to quantize

* [PT FE] Add dequantize example

* [PT FE] Implement replacer for quantized nodes

* [PT FE] Register replacer for quantize/dequantize

* [PT FE] Remove unwanted junk from previous version

* [PT FE] Fix building mistakes for frontend

* [PT FE] Clang fix

* [PT FE] Ease of use upgrade to quantize funcs

* [PT FE] Clang format

* [PT FE] Introduce new version of quantize/dequantize

* [PT FE] Remove unwanted files from new version

* [PT FE] Fix style

* [PT FE] Add QuantizedPtNode replacer, fix accuracy error

* [PT FE] Add improved version of quantize/dequantize with shared_ptrs

* [PT FE] Fix utils shared ptr reference error

* [PT FE] Quantize now takes correct input for operations

* [PT FE] Upgrade quantize method

* [PT FE] Add BFS for dequantize, add quantize_per_channel

* [PT FE] Add missing replacer to frontend, improve tests

* [PT FE] Rename replacer -> remover, remove unwanted header files

* [PT FE] Change function declarations to return ov::Output instead of shared ptr

* [PT FE] Add missing context mark node

* [PT FE] Remove unknown modifications to ie_c_api

* [PT FE] Remove fp16 support, turn off int32 tests

* [PT FE] Clang format

* [PT FE] Fix quantize_per_tensor

* [PT FE] Minor fixes from review

* [PT FE] Remove dequantize, remove helpers, replacer now removes nodes instead

* [PT FE] Rename Replacer to Remover for dequantize nodes

* [PT FE] Clang format

* [PT FE] Move comments to header files, minor import fixes

* [PT FE] Fix clang format

* [PT FE] Fix dtype issue

* [PT FE] Fix quantize_per_channel tests

* Apply suggestions from code review

Removing sporadic tests from precommit

* Apply suggestions from code review

* [PT FE] Fix conversion errors for aten::quantize_per_channel

* [PT FE] Mark axis 2 as xfail

---------

Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>
2023-07-20 10:49:20 +02:00
..
conftest.py
Add PyTorch Frontend (#15069)
2023-01-18 18:16:57 +04:00
pytorch_layer_test_class.py
Decompose/flatten tuple inputs (#18092)
2023-07-06 11:05:26 +04:00
test_adaptive_avg_pool3d.py
Torchscript backend (#17132)
2023-05-17 14:58:38 +02:00
test_adaptive_max_pool_2d.py
Torchscript backend (#17132)
2023-05-17 14:58:38 +02:00
test_add.py
Torchscript backend (#17132)
2023-05-17 14:58:38 +02:00
test_addcmul.py
[PT FE]: improve integration into mo.convert_model (#16243)
2023-03-24 16:55:07 +01:00
test_addmm.py
Fix sporadic fails when beta==0 in baddmm (#16610)
2023-03-28 18:47:35 +00:00
test_aliases.py
[PT FE] Support inplace operations on aliases of tensors (#17856)
2023-06-13 13:30:48 +02:00
test_all.py
[PT FE] Add aten::all implementation (#16901)
2023-05-02 21:12:12 +02:00
test_and.py
[PT FE] Add aten::__and__ operator with layer test (#15365)
2023-01-28 10:06:06 +03:00
test_arange.py
[PT FE]: fix arange dtype if it is not provided (#16084)
2023-03-04 10:17:09 +01:00
test_argmax_argmin.py
[PT FE]: support aten::argmax and aten::argmin (#17489)
2023-05-19 15:55:36 +00:00
test_argsort.py
[PT FE] Enable stable tests for sort & argsort (#16415)
2023-04-25 01:21:16 +04:00
test_batch_norm.py
Torchscript backend (#17132)
2023-05-17 14:58:38 +02:00
test_bitwise_not.py
[PT FE]: enable dtype in softmax and constant filling, extend logical ops support (#16276)
2023-03-20 14:12:12 +00:00
test_bool.py
Add support for concatenation in Loop (#15899)
2023-02-28 21:31:33 +01:00
test_cat.py
[PT FE] Support inplace operations on aliases of tensors (#17856)
2023-06-13 13:30:48 +02:00
test_chunk.py
[PT FE] Support inplace operations on aliases of tensors (#17856)
2023-06-13 13:30:48 +02:00
test_clamp.py
Add PyTorch Frontend (#15069)
2023-01-18 18:16:57 +04:00
test_clone.py
Add PyTorch Frontend (#15069)
2023-01-18 18:16:57 +04:00
test_comparision.py
Add eltwise types resolving. Support big int constants. (#15415)
2023-02-02 02:15:33 +01:00
test_conv_transposend.py
[PT FE]: support conv transpose (#15191)
2023-01-22 07:03:54 +00:00
test_convnd.py
[PT FE] Do not freeze for quantized models (#18082)
2023-06-15 19:41:06 +02:00
test_convolution_mode.py
Add PyTorch Frontend (#15069)
2023-01-18 18:16:57 +04:00
test_convolution.py
Torchscript backend (#17132)
2023-05-17 14:58:38 +02:00
test_copy.py
[PT FE] Support inplace operations on aliases of tensors (#17856)
2023-06-13 13:30:48 +02:00
test_cumsum.py
[PT FE]: add translation for aten::cumsum (#16092)
2023-03-08 11:07:29 +01:00
test_deformable_convolution.py
[PT FE] Add torchvision::deform_conv2d translation (#16450)
2023-03-27 11:13:32 +02:00
test_derive_index_range_length.py
[PT FE] Support inplace operations on aliases of tensors (#17856)
2023-06-13 13:30:48 +02:00
test_device.py
[PT FE] Add prim::device and prim::type, improvements to aten::to, aten::eq, aten::ne (#15881)
2023-03-01 09:46:55 +01:00
test_dict.py
[PT FE] Support prim::DictConstruct on the output (#16894)
2023-04-13 16:42:17 +00:00
test_distance.py
[PT FE]: support aten::cdist and aten::pairwise_distance (#17718)
2023-05-31 12:07:12 +02:00
test_div.py
Add eltwise types resolving. Support big int constants. (#15415)
2023-02-02 02:15:33 +01:00
test_einsum.py
[PT FE]: support aten::einsum (#15844)
2023-02-23 11:39:28 +04:00
test_embedding_bag.py
[Pt FE]: aten::embedding_bag (#17098)
2023-05-10 09:44:08 +02:00
test_embedding.py
[Pt FE]: aten::embedding_bag (#17098)
2023-05-10 09:44:08 +02:00
test_empty.py
[PT FE] Add aten::new_empty (#16312)
2023-03-20 10:03:33 +01:00
test_eq.py
add tests for aten::eq (#15222)
2023-01-21 21:07:47 +03:00
test_expand.py
[PT FE]: add more list construct transformations (#15614)
2023-02-15 16:39:27 +00:00
test_eye.py
[PT FE]: supports eye, tril, triu, tensor.fill_ and implicit scalars (#15187)
2023-01-25 21:04:56 +03:00
test_fake_quantize.py
[PT FE] Add translation for aten::fake_quantize_per_tensor_affine and aten::fake_quantize_per_channel_affine (#18176)
2023-07-07 09:05:23 +00:00
test_flatten.py
[PT FE] Fix aten::flatten, add more tests (#15576)
2023-02-10 14:23:27 +01:00
test_flip.py
[PT FE]: support flip operation (#17705)
2023-05-31 12:07:24 +02:00
test_floor_divide.py
[PT FE]: support mixed precision in floor divide (#16362)
2023-03-20 11:00:26 +01:00
test_fp16.py
[PT FE] Support bfloat16 constants (#18534)
2023-07-14 08:29:55 +02:00
test_full.py
[PT FE] Support inplace operations on aliases of tensors (#17856)
2023-06-13 13:30:48 +02:00
test_gather.py
[PT FE]: aten::gather (#16784)
2023-04-11 14:28:05 +04:00
test_gelu.py
[PT FE]: support aten::gelu with tanh approximate and tests (#15715)
2023-02-15 15:11:37 +01:00
test_getitem.py
Support more complicated cases of list concatenation (#16139)
2023-03-10 07:51:10 +01:00
test_glu.py
[PT FE]: support aten::glu and aten::sigmoid_ (#15185)
2023-01-21 21:05:20 +03:00
test_grid_sampler.py
[PT FE]: support grid sampler (#15243)
2023-01-31 14:04:37 +04:00
test_group_norm.py
Add PyTorch Frontend (#15069)
2023-01-18 18:16:57 +04:00
test_if.py
[CI] Introduce Windows pipeline in GitHub Actions (#18487)
2023-07-13 14:03:33 +04:00
test_im2col.py
Add PyTorch Frontend (#15069)
2023-01-18 18:16:57 +04:00
test_index_put_.py
[PT FE] Fix failing translation of aten::index_put_ (#16140)
2023-03-09 20:14:58 +00:00
test_index_select.py
[PT FE] fix invalid reshape shape after aten::index (#16821)
2023-04-11 12:41:59 +03:00
test_index.py
[PT FE] fix invalid reshape shape after aten::index (#16821)
2023-04-11 12:41:59 +03:00
test_instance_norm.py
[PT FE]: improve integration into mo.convert_model (#16243)
2023-03-24 16:55:07 +01:00
test_item.py
Add aten::item (#17730)
2023-05-26 18:05:24 +02:00
test_leaky_relu.py
[PT FE] Fix issues in multiple operations (#17418)
2023-05-22 10:35:34 +02:00
test_len.py
[PT FE] Fix aten::len for empty lists (#15820)
2023-02-20 21:34:04 +00:00
test_linear.py
[PT FE] Fix aten::flatten, add more tests (#15576)
2023-02-10 14:23:27 +01:00
test_listunpack.py
[PT FE] Fix issues in multiple operations (#17418)
2023-05-22 10:35:34 +02:00
test_log_softmax.py
[PT FE] Add aten::LogSoftmax (#17629)
2023-06-01 12:04:27 +00:00
test_log.py
Remove None at outputs of the model, improve types handling in frontend (#15258)
2023-01-25 13:28:47 +03:00
test_masked_fill.py
[PT FE]: update masked_fill support for multiple precisions (#15722)
2023-02-15 15:32:06 +04:00
test_mean.py
[PT FE]: fix aten::mean behaviour for provided dtype (#16790)
2023-04-11 14:29:29 +04:00
test_min_max.py
Fix typo in align types function (#18474)
2023-07-14 13:02:02 +02:00
test_mm.py
Add PyTorch Frontend (#15069)
2023-01-18 18:16:57 +04:00
test_mul.py
Add eltwise types resolving. Support big int constants. (#15415)
2023-02-02 02:15:33 +01:00
test_narrow.py
Add aten::narrow operator with layer test (#15788)
2023-02-20 15:47:25 +01:00
test_native_multi_head_attention.py
[PT FE] Add aten::_native_multi_head_attention (#17550)
2023-06-05 10:55:03 +02:00
test_nms.py
Add PyTorch Frontend (#15069)
2023-01-18 18:16:57 +04:00
test_nonzero.py
Add PyTorch Frontend (#15069)
2023-01-18 18:16:57 +04:00
test_norm.py
[PT FE]: support frobenius norm and fix aten::norm (#17701)
2023-05-29 11:14:16 +04:00
test_numel.py
Add PyTorch Frontend (#15069)
2023-01-18 18:16:57 +04:00
test_pad.py
[PT FE]: fix padding vaqlue dtype (#16087)
2023-03-04 11:08:56 +00:00
test_permute.py
[PT FE]: add more list construct transformations (#15614)
2023-02-15 16:39:27 +00:00
test_pooling.py
[PT FE] Support default strides for avg and max pooling (#17337)
2023-05-04 09:27:10 +02:00
test_pow.py
Fix issue with Pow when both inputs are scalars (#17305)
2023-05-02 16:49:42 +02:00
test_pythonop.py
[PT FE] Add prim::PythonOp (#15714)
2023-03-07 17:20:13 +01:00
test_quantize.py
[PT FE] Fix conversion for aten::quantize_per_channel (#18646)
2023-07-20 10:49:20 +02:00
test_remainder.py
[PT FE] Fix aten::squeeze translation + add tests for aten::slice (#17584)
2023-05-31 22:26:39 +02:00
test_repeat_interleave.py
[PT FE]: improve integration into mo.convert_model (#16243)
2023-03-24 16:55:07 +01:00
test_repeat.py
[PT FE]: add more list construct transformations (#15614)
2023-02-15 16:39:27 +00:00
test_reshape_as.py
Add PyTorch Frontend (#15069)
2023-01-18 18:16:57 +04:00
test_reshape.py
Add PyTorch Frontend (#15069)
2023-01-18 18:16:57 +04:00
test_rfftn_complex_transforms.py
[PT FE] Add aten::fft_rfftn and aten::fft_irfft complex replacers (#17999)
2023-06-16 11:35:30 +02:00
test_roi_align.py
[PT FE] Add torchvision::roi_align operator with layer test (#15821)
2023-02-23 09:26:17 +01:00
test_roll.py
Add PyTorch Frontend (#15069)
2023-01-18 18:16:57 +04:00
test_round.py
[PT FE]: multiple fixes for models from optimum testing scope (#18501)
2023-07-14 10:37:53 +04:00
test_rsub.py
[PT FE] Support set/get element type, shape and value in PyTorch FE InputModel (#16100)
2023-03-07 15:45:29 +01:00
test_scaled_dot_product_attention.py
[PT FE]: implement scaled dot product attention (#17178)
2023-04-26 12:51:02 +04:00
test_scatter.py
[PT FE] Add aten::scatter and inplace for aten::sub translation (#18341)
2023-07-11 11:00:50 +02:00
test_select.py
Add PyTorch Frontend (#15069)
2023-01-18 18:16:57 +04:00
test_selu.py
Add PyTorch Frontend (#15069)
2023-01-18 18:16:57 +04:00
test_set_item.py
Add support for aten::_set_item (#15643)
2023-02-14 14:11:51 +01:00
test_shape_as_tensor.py
[PT FE] Add aten::_shape_as_tensor (#17804)
2023-06-05 10:59:12 +02:00
test_sign.py
[PT FE]: aten::gather (#16784)
2023-04-11 14:28:05 +04:00
test_silu.py
Add PyTorch Frontend (#15069)
2023-01-18 18:16:57 +04:00
test_size.py
[PT FE]: support prim::min, prim::ListConstruct as output and fix aten::getitem for prim::ListConstruct (#15470)
2023-02-02 22:36:07 +00:00
test_slice.py
[PT FE] Fix aten::squeeze translation + add tests for aten::slice (#17584)
2023-05-31 22:26:39 +02:00
test_softmax.py
[PT FE]: enable dtype in softmax and constant filling, extend logical ops support (#16276)
2023-03-20 14:12:12 +00:00
test_sort.py
[PT FE] Enable stable sort layer tests (#17229)
2023-04-26 18:24:38 +02:00
test_split.py
Improve detectron2 support (#16011)
2023-03-23 22:30:03 +00:00
test_squeeze.py
[PT FE] Fix aten::squeeze translation + add tests for aten::slice (#17584)
2023-05-31 22:26:39 +02:00
test_stack.py
Add aten stack transformation (#15311)
2023-02-02 20:15:28 +01:00
test_strided_const.py
Add PyTorch Frontend (#15069)
2023-01-18 18:16:57 +04:00
test_sub.py
[PT FE] Add aten::scatter and inplace for aten::sub translation (#18341)
2023-07-11 11:00:50 +02:00
test_sum.py
[PT FE]: support boolean data type in sum operation (#17715)
2023-05-26 15:44:50 +04:00
test_to.py
[PyOV] Remove deprecated (#17512)
2023-05-16 21:48:39 +02:00
test_topk.py
[CI] Introduce Windows pipeline in GitHub Actions (#18487)
2023-07-13 14:03:33 +04:00
test_transpose.py
[PT FE]: support aten::t and inplace tril/triu (#18040)
2023-06-14 15:08:45 +04:00
test_trilu.py
[PT FE]: support aten::t and inplace tril/triu (#18040)
2023-06-14 15:08:45 +04:00
test_tuple_construct.py
Decompose/flatten tuple inputs (#18092)
2023-07-06 11:05:26 +04:00
test_type_as.py
Add PyTorch Frontend (#15069)
2023-01-18 18:16:57 +04:00
test_unary_ops.py
[PT FE] Support inplace operations on aliases of tensors (#17856)
2023-06-13 13:30:48 +02:00
test_unbind.py
Add PyTorch Frontend (#15069)
2023-01-18 18:16:57 +04:00
test_unflatten.py
[PT FE]: fix unflatten for list construct sizes (#18039)
2023-06-14 11:28:19 +04:00
test_unfold.py
[PT FE] Add aten::unfold operator with layer test (#15316)
2023-01-31 18:29:32 +01:00
test_unsqueeze.py
Add PyTorch Frontend (#15069)
2023-01-18 18:16:57 +04:00
test_upsample.py
[PT FE]: support upsamle2d bilinear and bicubic with antialias (#18617)
2023-07-19 09:36:11 +04:00
test_var_mean.py
[PT FE]: support aten::var_mean and aten::remainder (#15193)
2023-01-26 14:30:42 +00:00
test_view.py
[PT FE]: Add aten::view transformations (#15339)
2023-02-01 12:14:17 +01:00
test_where.py
Add PyTorch Frontend (#15069)
2023-01-18 18:16:57 +04:00