Commit Graph

318 Commits

Author SHA1 Message Date
alexlyulkov
72ad06bcf3
Merge pull request #25492 from alexlyulkov:al/range-fixed-5.x
Fixed ONNX Range layer to support any input type #25492

Fixed ONNX Range layer to support any input type

Extra PR: https://github.com/opencv/opencv_extra/pull/1173
Fixes #25363

### Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [x] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake
2024-04-26 18:59:43 +03:00
Alexander Smorkalov
43d243dd0e Merge branch 4.x 2024-04-22 11:08:39 +03:00
alexlyulkov
f9dd20eb07
Merge pull request #25414 from alexlyulkov:al/range-fixed
Fixed ONNX range layer #25414

Partially address https://github.com/opencv/opencv/issues/25363
Fixed ONNX range layer. It should support any input type.
Added tests (extra [PR](https://github.com/opencv/opencv_extra/pull/1170))

### Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [ ] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake
2024-04-17 09:38:21 +03:00
Alexander Smorkalov
282c762ead Merge branch 4.x 2024-04-10 11:27:47 +03:00
alexlyulkov
5144766380
Merge pull request #25277 from alexlyulkov:al/dnn-int-tests
Added int tests for CumSum, Scatter, Tile and ReduceSum dnn layers #25277

Fixed bug in tile layer.
Fixed bug in reduce layer by reimplementing the layer. 

Fixed types filter in Scatter and ScatterND layers

PR for extra: https://github.com/opencv/opencv_extra/pull/1161


### Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [ ] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake
2024-04-04 14:23:48 +03:00
Yuantao Feng
55d7e3f8cc
Merge pull request #1165 from fengyuentau:gold_yolo
[BugFix] dnn (ONNX): Foce dropping constant inputs in parseClip if they are shared #25319

Resolves https://github.com/opencv/opencv/issues/25278
Merge with https://github.com/opencv/opencv_extra/pull/1165

In Gold-YOLO ,`Div` has a constant input `B=6` which is then parsed into a `Const` layer in the ONNX importer, but `Clip` also has the shared constant input `max=6` which is already a `Const` layer and then connected to `Elementwise` layer. This should not happen because in the `forward()` of `Elementwise` layer, the legacy code goes through and apply activation to each input. More details on https://github.com/opencv/opencv/issues/25278#issuecomment-2032199630.

### Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [x] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake
2024-04-03 15:56:59 +03:00
Alexander Smorkalov
cb6d295f15 Merge branch 4.x 2024-04-02 16:39:54 +03:00
Yuantao Feng
b758897c29
Merge pull request #25271 from fengyuentau:matmul_bias
Merge with https://github.com/opencv/opencv_extra/pull/1158

Todo:

- [x] Fix Attention pattern recognition.
- [x] Handle other backends.

Benchmark:

"VIT_B_32 OCV/CPU", M1, results in milliseconds.

| Model | 4.x | This PR |
| - | - | - |
| VIT_B_32 OCV/CPU | 87.66 | **83.83** |


### Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [x] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake
2024-03-29 17:35:23 +03:00
Dmitry Kurtaev
cfa42e4338 Einsum OpenVINO backend 2024-03-29 14:29:45 +03:00
Dmitry Kurtaev
0b6c9a2123
Merge pull request #25181 from dkurt:release_conv_weights
Release convolution weightsMat after usage #25181

### Pull Request Readiness Checklist

related (but not resolved): https://github.com/opencv/opencv/issues/24134

Minor memory footprint improvement. Also, adds a test for VmHWM.

RAM top memory usage (-230MB)

| YOLOv3 (237MB file) |   4.x   |    PR   |
|---------------------|---------|---------|
| no winograd         | 808 MB  | 581 MB  |
| winograd            | 1985 MB | 1750 MB |

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [x] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake
2024-03-25 09:03:28 +03:00
alexlyulkov
85cc02f4de
Allowed int64 constants in ONNX parser (#25148)
* Removed automatic int64 to int32 conversion in ONNX parser

* Fixed wrong rebase code

* added tests, minor fixes

* fixed Cast layer

* Fixed Cast layer for fp16 backend

* Fixed Cast layer for fp16 backend

* Fixed Cast layer for fp16 backend

* Allowed uint32, int64, uint64 types in OpenCL

* Fixed Cast layer for fp16 backend

* Use randu in test_int

---------

Co-authored-by: Alexander Lyulkov <alexander.lyulkov@opencv.ai>
2024-03-13 11:48:23 +03:00
alexlyulkov
1d1faaabef
Merge pull request #24411 from alexlyulkov:al/dnn-type-inference
Added int32, int64 support and type inference to dnn #24411

**Added a type inference to dnn similar to the shape inference, added int32 and int64 support.**

- Added getTypes method for layers that calculates layer outputs types and internals types from inputs types (Similar to getMemoryShapes). By default outputs and internals types = input[0] type
- Added type inference pipeline similar to shape inference pipeline. LayersShapes struct (that is used in shape inference pipeline) now contains both shapes and types
- All layers output blobs are now allocated using the calculated types from the type inference.
- Inputs and constants with int32 and int64 types are not automatically converted into float32 now.
- Added int32 and int64 support for all the layers with indexing and for all the layers required in tests.

Added  int32 and int64 support for CUDA:
- Added host<->device data moving for int32 and int64
- Added int32 and int64 support for several layers (just slightly modified CUDA C++ templates)

Passed all the accuracy tests on CPU, OCL, OCL_FP16, CUDA, CUDA_FP16. (except RAFT model)

**CURRENT PROBLEMS**:
-  ONNX parser always converts int64 constants and layers attributes to int32, so some models with int64 constants doesn't work (e.g. RAFT). The solution is to disable int64->int32 conversion and fix attributes reading in a lot of ONNX layers parsers (https://github.com/opencv/opencv/issues/25102)
- I didn't add type inference and int support to VULCAN, so it doesn't work at all now.
- Some layers don't support int yet, so some unknown models may not work.

**CURRENT WORKAROUNDS**:
- CPU arg_layer indides are implemented in int32 followed by a int32->int64 conversion (the master branch has the same workaround with int32->float conversion)
- CPU and OCL pooling_layer indices are implemented in float followed by a float->int64 conversion
- CPU gather_layer indices are implemented in int32, so int64 indices are converted to int32 (the master branch has the same workaround with float->int32 conversion)

**DISABLED TESTS**:
- RAFT model

**REMOVED TESTS**:
- Greater_input_dtype_int64 (because it doesn't fit ONNX rules, the whole test is just comparing float tensor with int constant)

**TODO IN NEXT PULL REQUESTS**:
- Add int64 support for ONNX parser
- Add int support for more layers
- Add int support for OCL (currently int layers just run on CPU)
- Add int tests
- Add int support for other backends
2024-03-01 17:07:38 +03:00
Alexander Smorkalov
decf6538a2 Merge branch 4.x 2024-01-23 17:06:52 +03:00
Abduragim
0e6b7f1656 fix 1D handling issue in inner product 2024-01-22 20:10:34 +04:00
Alexander Smorkalov
c739117a7c Merge branch 4.x 2024-01-19 17:32:22 +03:00
Abduragim
d30bf1bc3c added test for yolo nas 2024-01-17 13:01:43 +03:00
Yuantao Feng
7fb336322d
Merge pull request #24808 from fengyuentau:fix_layernorm
dnn: no layer norm fusion if axes.back() is not the axis of last dimension #24808

Merge with https://github.com/opencv/opencv_extra/pull/1137

Resolves https://github.com/opencv/opencv/issues/24797

### Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [x] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [ ] The feature is well documented and sample code can be built with the project CMake
2024-01-10 13:01:00 +03:00
Abduragim
6c28d7140a 1d support for einsum 2024-01-08 21:34:47 +03:00
Abduragim Shtanchaev
3b26e183cb changed weights of yolov7 2023-12-28 23:03:47 +03:00
Yuantao Feng
f978c99523
Merge pull request #24753 from fengyuentau:einsum_importer
dnn onnx: support constaint inputs in einsum importer #24753 

Merge with https://github.com/opencv/opencv_extra/pull/1132.

Resolves https://github.com/opencv/opencv/issues/24697

Credits to @LaurentBerger.

---

This is a workaround. I suggest to get input shapes and calculate the output shapes in `getMemoryShapes` so as to keep the best compatibility. It is not always robust getting shapes during the importer stage and we should avoid that as much as possible.

### Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [x] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake
2023-12-25 14:42:05 +03:00
Alexander Alekhin
f49b26182b dnn(test): skip very long debug tests, reduce test time 2023-12-25 08:44:06 +00:00
Alexander Alekhin
96b894e0e1 Merge pull request #24761 from opencv-pushbot:gitee/alalek/test_skip_update_win32 2023-12-25 08:27:30 +00:00
Alexander Alekhin
f8502d45f9 dnn(test): skip tests on 32-bit Windows 2023-12-25 07:23:45 +00:00
Alexander Smorkalov
53cd921ab4 Increate Vit_b test threshold a bit for CUDA FP16. 2023-12-22 13:37:44 +03:00
Alexander Alekhin
c9bb92d58b dnn(test): tune FP16 test tolerance 2023-12-21 13:39:05 +00:00
Yuantao Feng
0521a3a384
Merge pull request #24476 from fengyuentau:attention_layer
dnn: add attention layer #24476

Resolves #24609

Merge with: https://github.com/opencv/opencv_extra/pull/1128.

Attention operator spec from onnxruntime: https://github.com/microsoft/onnxruntime/blob/v1.16.1/docs/ContribOperators.md#com.microsoft.Attention.

TODO:
- [x] benchmark (before this PR vs. with this PR vs. ORT).
- [x] Layer fusion: Take care Slice with end=INT64_MAX.
- [x] Layer fusion: match more potential attention (VIT) patterns.
    - [x] Single-head attention is supported.
- [x] Test AttentionSubgraph fusion.
- [x] Add acc tests for VIT_B_32 and VitTrack
- [x] Add perf tests for VIT_B_32 and VitTrack

## Benchmarks

Platform: Macbook Air M1.

### Attention Subgraph

Input scale: [1, 197, 768].

|                        | mean (ms) | median (ms) | min (ms) |
| ---------------------- | --------- | ----------- | -------- |
| w/ Attention (this PR) | 3.75      | 3.68        | 3.22     |
| w/o Attention          | 9.06      | 9.01        | 8.24     |
| ORT (python)           | 4.32      | 2.63        | 2.50     |

### ViTs

All data in millisecond (ms).

| ViTs     | With Attention | Without Attention | ORT    |
| -------- | -------------- | ----------------- | ------ |
| vit_b_16 | 302.77         | 365.35            | 109.70 |
| vit_b_32 | 89.92          | 116.22            | 30.36  |
| vit_l_16 | 1593.32        | 1730.74           | 419.92 |
| vit_l_32 | 468.11         | 577.41            | 134.12 |
| VitTrack | 3.80           | 3.87              | 2.25   |

### Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [x] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake
2023-12-20 19:35:07 +03:00
Abduragim Shtanchaev
d3dd2e463c
Merge pull request #24611 from Abdurrahheem:ash/add_yolov6_test
Add test for YoloX Yolo v6 and Yolo v8 #24611

This PR adds test for YOLOv6 model (which was absent before)
The onnx weights for the test are located in this PR [ #1126](https://github.com/opencv/opencv_extra/pull/1126)

### Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [ ] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake
2023-12-11 16:42:51 +03:00
skycat8
848dd12a1f
Merge pull request #24553 from skycat8:yolov5
Add yolov5n to tests #24553

### Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [ X] I agree to contribute to the project under Apache 2 License.
- [ X] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [ X] The PR is proposed to the proper branch
- [ X] There is a reference to the original bug report and related work
- [ X] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [ X] The feature is well documented and sample code can be built with the project CMake
2023-11-24 10:36:06 +03:00
zihaomu
b913e73d04
DNN: add the Winograd fp16 support (#23654)
* add Winograd FP16 implementation

* fixed dispatching of FP16 code paths in dnn; use dynamic dispatcher only when NEON_FP16 is enabled in the build and the feature is present in the host CPU at runtime

* fixed some warnings

* hopefully fixed winograd on x64 (and maybe other platforms)

---------

Co-authored-by: Vadim Pisarevsky <vadim.pisarevsky@gmail.com>
2023-11-20 13:45:37 +03:00
Yuantao Feng
a478757483
Merge pull request #24544 from fengyuentau:layernorm_conformance
dnn test: move layer norm tests into conformance tests #24544

Merge with https://github.com/opencv/opencv_extra/pull/1122

## Motivation

Some ONNX operators, such as `LayerNormalization`, `BatchNormalization` and so on, produce outputs for training (mean, stdev). So they have reference outputs of conformance tests for those training outputs as well. However, when it comes to inference, we do not need and produce those outputs for training here in dnn. Hence, output size does not match if we use dnn to infer those conformance models. This has become the barrier if we want to test these operators using their conformance tests.

<!--
| Operator                | Inference needed                    | Outputs (required - total) | Optional outputs for training? |
| ----------------------- | ----------------------------------- | -------------------------- | ------------------------------ |
| BatchNormalization      | Yes                                 | 1 - 3                      | Yes                            |
| Dropout                 | Maybe, can be eliminated via fusion | 1 - 2                      | Yes                            |
| GRU                     | Yes                                 | 0 - 2                      | No                             |
| LSTM                    | Yes                                 | 0 - 3                      | No                             |
| LayerNormalization      | Yes                                 | 1 - 3                      | Yes                            |
| MaxPool                 | Yes                                 | 1 - 2                      | Yes                            |
| RNN                     | Yes                                 | 0 - 2                      | No                             |
| SoftmaxCrossEntropyLoss | No                                  | 1 - 2                      | --                             |
-->

**I checked all ONNX operators with optional outputs. Turns out there are only `BatchNormalization`, `Dropout`, `LayerNormalization` and `MaxPool` has optional outputs for training. All except `LayerNormalization` have models set for training mode and eval mode. Blame ONNX for that.**

## Solution

In this pull request, we remove graph outputs if the graph looks like the following:

```
    [X]   [Scale]  [Bias]                      [X]   [Scale]  [Bias]
      \      |      /         this patch         \      |      /
     LayerNormalization      ----------->       LayerNormalization
      /      |      \                                   |
    [Y]    [Mean]  [Stdev]                             [Y]
```

We can update conformance tests and turn on some cases as well if extending to more layers.

Notes:
1. This workaround does not solve expanded function operators if they are fused into a single operator, such as `$onnx/onnx/backend/test/data/node/test_layer_normalization_2d_axis1_expanded`, but they can be run without fusion. Note that either dnn or onnxruntime does not fuse those expanded function operators.

### Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [x] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake
2023-11-20 11:19:24 +03:00
fengyuentau
031846f2e1 remove filter 2023-11-13 14:47:40 +08:00
Alexander Smorkalov
34f34f6227 Merge branch 4.x 2023-11-08 14:39:48 +03:00
Dmitry Kurtaev
fa56623458
Merge pull request #24463 from dkurt:dnn_shared_nodes_fusion
DNN graph fusion with shared nodes #24463

### Pull Request Readiness Checklist

For now, nodes from matched pattern are removed during the matching process so if nodes are used in similar subgraph, they cannot be found.

required for https://github.com/opencv/opencv/pull/24397

**Merge with extra**: https://github.com/opencv/opencv_extra/pull/1115

A part from [model_name ](https://github.com/onnx/models/blob/main/vision/object_detection_segmentation/fcn/model/fcn-resnet101-11.onnx) with two Resize subgraphs with shared nodes:
![image](https://github.com/opencv/opencv/assets/25801568/611d89d9-12fb-4add-9218-13b10d2c086a)

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [x] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake
2023-11-03 12:34:09 +03:00
Abduragim Shtanchaev
a3b3a589f9
Merge pull request #24322 from Abdurrahheem:ash/dev_einsum_ellips
Ellipses supported added for Einsum Layer #24322

This PR added addresses issues not covered in #24037. Namely these are: 
Test case for this patch is in this PR [#1106](https://github.com/opencv/opencv_extra/pull/1106) in opencv extra

Added: 
 - [x] Broadcasting reduction "...ii ->...I"
 - [x] Add lazy shape deduction. "...ij, ...jk->...ik"
 
 Features to add: 
- [ ] Add implicit output computation support. "bij,bjk ->" (output subscripts should be "bik")
- [ ] Add support for CUDA backend 
- [ ] BatchWiseMultiply optimize
- [ ] Performance test

### Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [x] There is a reference to the original bug report and related work
- [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake
2023-10-24 16:47:00 +03:00
Alexander Smorkalov
97620c053f Merge branch 4.x 2023-10-23 11:53:04 +03:00
Aser Atawya
240b245105
Merge pull request #24092 from Aser-Abdelfatah:GSoC_Support_GatherElements_ONNX
GSoC Add ONNX Support for GatherElements #24092

Merge with: https://github.com/opencv/opencv_extra/pull/1082
Adds support to the ONNX operator GatherElements [operator docs](https://github.com/onnx/onnx/blob/main/docs/Operators.md#GatherElements)
Added tests to opencv_extra at pull request https://github.com/opencv/opencv_extra/pull/1082

### Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [x] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake
2023-10-18 10:41:47 +03:00
alexlyulkov
014e8485b5
Merge pull request #24367 from alexlyulkov:al/fixed-cumsum-inplace-flag
Fixed CumSum layer inplace flag #24367

When exclusive is false:
dst[i] = dst[i-1] + src[i]
When exclusive is true:
dst[i] = dst[i-1] + src[i-1]
So CumSum layer can be inplace only when exclusive flag is false.
2023-10-18 09:21:40 +03:00
Yuantao Feng
0507043a55
Merge pull request #24386 from fengyuentau:fix_dtype_nary_eltwise
dnn: fix inconsistent input dtype for nary eltwise layers #24386

Resolves https://github.com/opencv/opencv/issues/24385
Merge with https://github.com/opencv/opencv_extra/pull/1107
Relates https://github.com/opencv/opencv/pull/24092#discussion_r1353964405

### Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [x] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake
2023-10-13 11:56:18 +03:00
Yuantao Feng
590f150d5e
dnn: hotfixes for fast gemm (#24315)
* remove Conformance from test names

* integrate neon optimization into default

* quick fix: define CV_NEON_AARCH64 0 for non NEON platforms

* remove var batch that leads to memory leak

* put neon code back to fast_gemm_kernels.simd

* reorganize code to reduce duplicate code
2023-10-07 21:48:44 +03:00
Dmitry Kurtaev
2c92eb3175 Enable more tests for OpenVINO 2023.0 2023-10-05 12:51:55 +03:00
Alexander Smorkalov
163d544ecf Merge branch 4.x 2023-10-02 10:17:23 +03:00
Dmitry Kurtaev
c7ec0d599a
Merge pull request #23987 from dkurt:openvino_int8_backend
OpenVINO backend for INT8 models #23987

### Pull Request Readiness Checklist

TODO:
- [x] DetectionOutput layer (https://github.com/opencv/opencv/pull/24069)
- [x] Less FP32 fallbacks (i.e. Sigmoid, eltwise sum)
- [x] Accuracy, performance tests (https://github.com/opencv/opencv/pull/24039)
- [x] Single layer tests (convolution)
- [x] ~~Fixes for OpenVINO 2022.1 (https://pullrequest.opencv.org/buildbot/builders/precommit_custom_linux/builds/100334)~~


Performace results for object detection model `coco_efficientdet_lite0_v1_1.0_quant_2021_09_06.tflite`:
| backend | performance (median time) |
|---|---|
| OpenCV | 77.42ms |
| OpenVINO 2023.0 | 10.90ms |

CPU: `11th Gen Intel(R) Core(TM) i5-1135G7 @ 2.40GHz`

Serialized model per-layer stats (note that Convolution should use `*_I8` primitives if they are quantized correctly): https://gist.github.com/dkurt/7772bbf1907035441bb5454f19f0feef

---

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [x] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake
2023-09-28 16:24:43 +03:00
fengyuentau
7fa0493ca0 init commit 2023-09-28 11:50:21 +08:00
Yuantao Feng
bb171a0c05
dnn: expand refactor with cv::broadcast for onnx models (#24295)
* add expand impl with cv::broadcast

* remove expandMid

* deduce shape from -1

* add constant folding

* handle input constant; handle input constant 1d

* add expand conformance tests; add checks to disallow shape of neg values; add early copy for unchanged total elements

* fix ExpandSubgraph

* dummy commit to trigger build

* dummy commit to trigger build 1

* remove conformance from test names
2023-09-27 09:28:52 +03:00
Abduragim Shtanchaev
865e7cacca
Merge pull request #24037 from Abdurrahheem:ash/dev_einsum
Add Support for Einsum Layer #24037

### This PR adding support for [Einsum Layer](https://pytorch.org/docs/stable/generated/torch.einsum.html) (in progress). 

This PR is currently not to be merged but only reviewed. Test cases are located in [#1090](https://github.com/opencv/opencv_extra/pull/1090)RP in OpenCV extra

**DONE**: 
 - [x] 2-5D GMM support added
 - [x] Matrix transpose support added
 - [x] Reduction type comupte  'ij->j'
 - [x] 2nd shape computation - during forward 

**Next PRs**:
- [ ] Broadcasting reduction "...ii ->...i"
- [ ] Add lazy shape deduction. "...ij, ...jk->...ik"
- [ ] Add implicit output computation support. "bij,bjk ->" (output subscripts should be "bik")
- [ ] Add support for CUDA backend 
- [ ] BatchWiseMultiply optimize

**Later in 5.x version (requires support for 1D matrices)**: 
- [ ] Add 1D vector multiplication support 
- [ ] Inter product "i, i" (problems with 1D shapes)

### Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [ ] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake
2023-09-22 11:25:02 +03:00
Vadim Pisarevsky
416bf3253d
attempt to add 0d/1d mat support to OpenCV (#23473)
* attempt to add 0d/1d mat support to OpenCV

* revised the patch; now 1D mat is treated as 1xN 2D mat rather than Nx1.

* a step towards 'green' tests

* another little step towards 'green' tests

* calib test failures seem to be fixed now

* more fixes _core & _dnn

* another step towards green ci; even 0D mat's (a.k.a. scalars) are now partly supported!

* * fixed strange bug in aruco/charuco detector, not sure why it did not work
* also fixed a few remaining failures (hopefully) in dnn & core

* disabled failing GAPI tests - too complex to dig into this compiler pipeline

* hopefully fixed java tests

* trying to fix some more tests

* quick followup fix

* continue to fix test failures and warnings

* quick followup fix

* trying to fix some more tests

* partly fixed support for 0D/scalar UMat's

* use updated parseReduce() from upstream

* trying to fix the remaining test failures

* fixed [ch]aruco tests in Python

* still trying to fix tests

* revert "fix" in dnn's CUDA tensor

* trying to fix dnn+CUDA test failures

* fixed 1D umat creation

* hopefully fixed remaining cuda test failures

* removed training whitespaces
2023-09-21 18:24:38 +03:00
Yuantao Feng
8a96e34e33
dnn: add gemm_layer in place of fully_connected_layer for onnx models (#23897)
* first commit

* turned C from input to constant; force C constant in impl; better handling 0d/1d cases

* integrate with gemm from ficus nn

* fix const inputs

* adjust threshold for int8 tryQuantize

* adjust threshold for int8 quantized 2

* support batched gemm and matmul; tune threshold for rcnn_ilsvrc13; update googlenet

* add gemm perf against innerproduct

* add perf tests for innerproduct with bias

* fix perf

* add memset

* renamings for next step

* add dedicated perf gemm

* add innerproduct in perf_gemm

* remove gemm and innerproduct perf tests from perf_layer

* add perf cases for vit sizes; prepack constants

* remove batched gemm; fix wrong trans; optimize KC

* remove prepacking for const A; several fixes for const B prepacking

* add todos and gemm expression

* add optimized branch for avx/avx2

* trigger build

* update macros and signature

* update signature

* fix macro

* fix bugs for neon aarch64 & x64

* add backends: cuda, cann, inf_ngraph and vkcom

* fix cuda backend

* test commit for cuda

* test cuda backend

* remove debug message from cuda backend

* use cpu dispatcher

* fix neon macro undef in dispatcher

* fix dispatcher

* fix inner kernel for neon aarch64

* fix compiling issue on armv7; try fixing accuracy issue on other platforms

* broadcast C with beta multiplied; improve func namings

* fix bug for avx and avx2

* put all platform-specific kernels in dispatcher

* fix typos

* attempt to fix compile issues on x64

* run old gemm when neon, avx, avx2 are all not available; add kernel for armv7 neon

* fix typo

* quick fix: add macros for pack4

* quick fix: use vmlaq_f32 for armv7

* quick fix for missing macro of fast gemm pack f32 4

* disable conformance tests when optimized branches are not supported

* disable perf tests when optimized branches are not supported

* decouple cv_try_neon and cv_neon_aarch64

* drop googlenet_2023; add fastGemmBatched

* fix step in fastGemmBatched

* cpu: fix initialization ofb; gpu: support batch

* quick followup fix for cuda

* add default kernels

* quick followup fix to avoid macro redef

* optmized kernels for lasx

* resolve mis-alignment; remove comments

* tune performance for x64 platform

* tune performance for neon aarch64

* tune for armv7

* comment time consuming tests

* quick follow-up fix
2023-09-20 00:53:34 +03:00
Dmitry Kurtaev
4b8aeb1129
Merge pull request #24039 from dkurt:tflite_test_backends
TFLite models on different backends (tests and improvements) #24039

### Pull Request Readiness Checklist

* MaxUnpooling with OpenVINO
* Fully connected with transposed inputs/weights with OpenVINO
* Enable backends tests for TFLite (related to https://github.com/opencv/opencv/issues/23992#issuecomment-1640691722)
* Increase existing tests thresholds

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [x] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake
2023-08-04 11:28:51 +03:00
Dmitry Kurtaev
96f23e3da1
Merge pull request #24080 from dkurt:dnn_cuda_layers
Resolve uncovered CUDA dnn layer #24080

### Pull Request Readiness Checklist

* Gelu activation layer on CUDA
* Try to relax GEMM from ONNX

resolves https://github.com/opencv/opencv/issues/24064

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [x] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake
2023-08-03 09:13:42 +03:00
Dmitry Kurtaev
6909fffde1 Consider half pixel mode in ONNX resize 2023-06-14 14:21:28 +03:00