Commit Graph

2426 Commits

Author SHA1 Message Date
Alexander Lyulkov
759fc701ab Fixed cumsum layer, enablem conformance tests 2024-06-14 13:02:57 +03:00
Abduragim Shtanchaev
a2d2ea6536
Merge pull request #25727 from Abdurrahheem:ash/comf-denylist-reduce
Additional Comments for Conformance Denylist #25727

This PR adds additional comments on conformance denylist. Once  BOOL type got support in 5.x, some test layer changed their failing issue.

### 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
2024-06-10 13:51:47 +03:00
Dmitry Kurtaev
3700f9e1e9
Merge pull request #25709 from dkurt:wrap_addLayer
* Wrap dnn addLayer
* Add typing stubs
2024-06-07 20:39:44 +03:00
alexlyulkov
70df023317
Merge pull request #25605 from alexlyulkov:al/bool-dnn
Added bool support to dnn #25605

Added bool support to dnn pipeline (CPU, OpenVINO and CUDA pipelines).

Added bool support to these layers(CPU and OpenVINO):
- Equal, Greater, GreaterOrEqual, Less, LessOrEqual
- Not
- And, Or, Xor
- Where

Enabled all the conformance tests for these layers.

### 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
2024-06-06 12:52:06 +03:00
Kumataro
1bd5ca1ebe
Merge pull request #25686 from Kumataro:fix25674
Suppress build warnings for GCC14 #25686

Close #25674

### 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.
- [ ] The feature is well documented and sample code can be built with the project CMake
2024-06-02 14:14:04 +03:00
CNOCycle
98b8825031
Merge pull request #25613 from CNOCycle:tflite/ops
Support Global_Pool_2D ops in .tflite model #25613

### Pull Request Readiness Checklist

**Merge with extra**: https://github.com/opencv/opencv_extra/pull/1180

This PR adds support for `GlobalAveragePooling2D` and `GlobalMaxPool2D` on the TFlite backend. When the k`eep_dims` option is enabled, the output is a 2D tensor, necessitating the inclusion of an additional flatten layer. Additionally, the names of these layers have been updated to match the output tensor names generated by `generate.py` from the opencv_extra repository.

- [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
2024-05-31 19:31:21 +03:00
Abduragim Shtanchaev
d7f04a9d33
Merge pull request #25660 from Abdurrahheem:ash/fix-slice-empty-input
Slice layer parser fix to support empty input case #25660

This PR fixes Slice Layer's parser to handle empty input cases (cases with initializer)
It fixed the issue rased in #24838

### 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
2024-05-31 13:13:36 +03:00
Danial Javady
05e48605a0
Merge pull request #25412 from ZelboK:update-cudnn-to-9
Refactor DNN module to build with cudnn 9 #25412

A lot of APIs that are currently being used in the dnn module have been removed in cudnn 9. They were deprecated in 8. 
This PR updates said code accordingly to the newer API.

Some key notes:
1) This is my first PR. I am new to openCV. 
2) `opencv_test_core` tests pass
3) On a 3080, cuda 12.4(should be irrelevant since I didn't build the `opencv_modules`, gcc 11.4, WSL 2. 
4) For brevity I will avoid including macro code that will allow for older versions of cudnn to build.

I was unable to get the tests working for `opencv_test_dnn` and `opencv_perf_dnn`. The errors I get are of the following: 
```
 OpenCV tests: Can't find required data file: dnn/onnx/conformance/node/test_reduce_prod_default_axes_keepdims_example/model.onnx in function 'findData'
" thrown in the test body.
```
So before I spend more time investigating I was hoping to get a maintainer to point me in the right direction here. I would like to run these tests and confirm things are working as intended. I may have missed some details.


### Pull Request Readiness Checklist

relevant issue
(https://github.com/opencv/opencv/issues/24983

- [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
- [ ] 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.
- [ ] The feature is well documented and sample code can be built with the project CMake
2024-05-28 09:54:08 +03:00
Abduragim Shtanchaev
1f874028fb fixed for openvino einsum 2024-05-22 10:30:10 +04:00
Abduragim Shtanchaev
6feb765ebb
Merge pull request #25116 from Abdurrahheem:ash/elementwise-1d-test
Element-wise test for 1D #25116

This PR introduces 1D parametrized test for element wise layer. The means that the tests covers following layer: 

`Clip`, `ReLU6`, `ReLU`,
                        `GeLU`, `GeluApprox`, `TanH`,
                        `Swish`, `Mish`, `Sigmoid`,
                        `ELULayer`, `Abs`, `BNLL`,
                        `Ceil`, `Floor`, `LogLayer`,
                        `Round`, `Sqrt`, `Acos`,
                        `Acosh`, `Asin`, `Asinh`,
                        `Atan`, `Atanh`, `Cos`,
                        `Sin`, `Sinh`, `Tan`, `Erf`,
                        `Reciprocal`, `Cosh`, `HardSwish`,
                        `Softplus`, `Softsign`, `Celu`,
                        `HardSigmid`, `Selu`, `ThresholdedRelu`,
                        `Power`, `Exp`, `Sign`, `Shrink`,
                        `ChannelsPReLU`

Not sure if this is best way to implement this 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
- [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
2024-05-21 14:05:01 +03:00
Abduragim Shtanchaev
f676cb3c62
Merge pull request #25595 from Abdurrahheem:ash/01D-einsum-test
Add support for scalar and matrix multiplication in einsum #25595

### 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
2024-05-21 13:36:12 +03:00
Alexander Smorkalov
0b39a51be8 pre: OpenCV 4.10.0 (version++). 2024-05-21 11:37:05 +03:00
Alexander Smorkalov
5f509e2ec1 Skip Test_Caffe_layers.Concat with Vulkan due to sporadic failures. 2024-05-17 11:54:25 +03:00
Yuantao Feng
bc0618b688
Merge pull request #25582 from fengyuentau:dnn/dump_pbtxt
Current net exporter `dump` and `dumpToFile` exports the network structure (and its params) to a .dot file which works with `graphviz`. This is hard to use and not friendly to new user. What's worse, the produced picture is not looking pretty.
dnn: better net exporter that works with netron #25582

This PR introduces new exporter `dumpToPbtxt` and uses this new exporter by default with environment variable `OPENCV_DNN_NETWORK_DUMP`. It mimics the string output of a onnx model but modified with dnn-specific changes, see below for an example.

![image](https://github.com/opencv/opencv/assets/17219438/0644bed1-da71-4019-8466-88390698e4df)

## Usage

Call `cv::dnn::Net::dumpToPbtxt`:

```cpp
TEST(DumpNet, dumpToPbtxt) {
    std::string path = "/path/to/model.onnx";
    auto net = readNet(path);

    Mat input(std::vector<int>{1, 3, 640, 480}, CV_32F);
    net.setInput(input);

    net.dumpToPbtxt("yunet.pbtxt");
}
```

Set `export OPENCV_DNN_NETWORK_DUMP=1`

```cpp
TEST(DumpNet, env) {
    std::string path = "/path/to/model.onnx";
    auto net = readNet(path);

    Mat input(std::vector<int>{1, 3, 640, 480}, CV_32F);
    net.setInput(input);

    net.forward();
}
```

---

Note:
- `pbtxt` is registered as one of the ONNX model suffix in netron. So you can see `module: ai.onnx` and such in the model.
- We can get the string output of an ONNX model with the following script

```python
import onnx
net = onnx.load("/path/to/model.onnx")
net_str = str(net)
file = open("/path/to/model.pbtxt", "w")
file.write(net_str)
file.close()
```

### 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
- [ ] 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
2024-05-17 11:07:05 +03:00
alexlyulkov
9238eb2ab2
Merge pull request #25555 from alexlyulkov:al/int8-uint8-dnn-input
Disabled conversion to float of model's input #25555

In dnn 4.x usually any model's input is converted to float32 or float16 (except quantized models). Also mean and scale can be applied. In current dnn 5.x there is the same conversion except int32 and int64 types. I removed this conversion.

Here is how the pipeline works now:
- if input Mat type is float32, the pipeline applies mean and scale and may convert it to float16.
- if input Mat type is not float32, the pipeline preserves the input type and doesn't apply mean and scale

There was a conflict in protobuf parser between ONNX importer and tests. In ONNX importer any uint8 weight was handled as quantized weight and x = int8(x_uint8 - 128) conversion was used inside the protobuf parser. ONNX conformance tests used the same protobuf reader, so tests with uint8 inputs couldn't read the input values properly. I've made this conversion optional.

These ONNX conformance tests are enabled:
- test_add_uint8
- test_div_uint8
- test_mul_uint8
- test_sub_uint8
- test_max_int8
- test_max_uint8
- test_min_int8
- test_min_uint8
- test_mod_mixed_sign_int8
- test_mod_uint8

These tests were removed:
- Test_two_inputs.basic (when input is uint8)
- setInput.normalization (when input is uint8)

### 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
2024-05-16 15:54:00 +03:00
Alexander Smorkalov
78ed6de518
Merge pull request #25594 from LaurentBerger:I25587
typo
2024-05-16 08:46:56 +03:00
CNOCycle
7713c84465
Merge pull request #25297 from CNOCycle:tflite/transpose
Support Transpose op in TFlite #25297

**Merge with extra**: https://github.com/opencv/opencv_extra/pull/1168

The purpose of this PR is to introduce support for the Transpose op in TFlite format and to add a shape comparison between the output tensors and the references. In some occasional cases, the shape of the output tensor is `[1,4,1,1]`, while the shape of the reference tensor is `[1,4]`. Consequently, the norm check incorrectly reports that the test has passed, as the residual is zero.

Below is a Python script for generating testing data. The generated data can be integrated into the repo `opencv_extra`.

```python
import numpy as np
import tensorflow as tf

PREFIX_TFL = '/path/to/opencv_extra/testdata/dnn/tflite/'

def generator(input_tensor, model, saved_name):

    # convert keras model to .tflite format
    converter = tf.lite.TFLiteConverter.from_keras_model(model)
    #converter.optimizations = [tf.lite.Optimize.DEFAULT]
    converter.optimizations = [None]
    tflite_model = converter.convert()
    with open(f'{PREFIX_TFL}/{saved_name}.tflite', 'wb') as f:
        f.write(tflite_model)

    # save the input tensor to .npy
    if input_tensor.ndim == 4:
        opencv_tensor = np.transpose(input_tensor, (0,3,1,2))
    else:
        opencv_tensor = input_tensor
    opencv_tensor = np.copy(opencv_tensor, order='C').astype(np.float32)
    np.save(f'{PREFIX_TFL}/{saved_name}_inp.npy', opencv_tensor)

    # generate output tenosr and save it to .npy
    mat_out = model(input_tensor).numpy()
    mat_out = np.copy(mat_out, order='C').astype(np.float32)
    if mat_out.ndim == 4:
        mat_out = np.transpose(mat_out, (0,3,1,2))
    interpreter = tf.lite.Interpreter(model_content=tflite_model)
    out_name = interpreter.get_output_details()[0]['name']
    np.save(f'{PREFIX_TFL}/{saved_name}_out_{out_name}.npy', mat_out)

def build_transpose():

    model_name = "keras_permute"
    mat_in = np.array([[[1,2,3], [4,5,6]]], dtype=np.float32)

    model = tf.keras.Sequential()
    model.add(tf.keras.Input(shape=(2,3)))
    model.add(tf.keras.layers.Permute((2,1)))
    model.summary()

    generator(mat_in, model, model_name)

if __name__ == '__main__':
    build_transpose()
```

### Pull Request Readiness Checklist

- [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
- [ ] 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
2024-05-15 20:07:25 +03:00
unknown
5009109167 typo 2024-05-15 16:16:07 +02:00
Laurent Berger
76d9f7aaeb
Merge pull request #25591 from LaurentBerger:I25589
Remove dnn::layer::allocate in doc #25591

### 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 #25589 
- [ ] 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
2024-05-15 17:08:52 +03:00
alexlyulkov
6af0394cd2
Merge pull request #25458 from alexlyulkov:al/dnn-openvino-int-support
Added int support for OpenVINO dnn backend #25458

Modified dnn OpenVINO integration to support type inference and int operations.

Added OpenVINO support to Cast, CumSum, Expand, Gather, GatherElements, Scatter, ScatterND, Tile layers.
I tried to add Reduce layer, but looks like OpenVINO uses float values inside Reduce operation so it can't pass our int tests.

OpenVINO uses int32 precision for int64 operations, so I've modified input values for int64 tests when backend is OpenVINO.

OpenVINO has a strange behavior with custom layers and int64 values. After model compilation OpenVINO may change types, so the model can have different output type. That's why these tests were disabled:
- Test_ArgMax_Int.random/0, where GetParam() = (4, NGRAPH/CPU)
- Test_ArgMax_Int.random/6, where GetParam() = (11, NGRAPH/CPU)
- Test_Reduce_Int.random/6, where GetParam() = (11, NGRAPH/CPU)
- Test_Reduce_Int.two_axes/6, where GetParam() = (11, NGRAPH/CPU)

Also these tests were temporary disabled, they didn't work on both 4.x and 5.x branches:
- Test_Caffe_layers.layer_prelu_fc/0, where GetParam() = NGRAPH/CPU
- Test_ONNX_layers.LSTM_Activations/0, where GetParam() = NGRAPH/CPU
- Test_ONNX_layers.Quantized_Convolution/0, where GetParam() = NGRAPH/CPU
- Test_ONNX_layers.Quantized_Eltwise_Scalar/0, where GetParam() = NGRAPH/CPU
- Test_TFLite.EfficientDet_int8/0, where GetParam() = NGRAPH/CPU


### 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
2024-05-15 11:51:59 +03:00
Abduragim Shtanchaev
5bdc41964a
Merge pull request #25487 from Abdurrahheem:ash/01D-additional-fixes
Additional fixes to 0/1D tests #25487

This has additional fixes requited for 0/1D tests.

### 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
2024-05-15 10:50:03 +03:00
Abduragim Shtanchaev
5260b48695
Merge pull request #25390 from Abdurrahheem:ash/0d-padding-layer
1/0D test padding layer #25390

This PR introduces 0/1D test for `padding` layer.

### 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
2024-05-15 10:26:26 +03:00
Abduragim Shtanchaev
17e6b3f931
Merge pull request #25409 from Abdurrahheem:ash/0D-tile-test
0/1D test for tile layer #25409

This PR introduces `0/1D` test for `Tile` layer. It also add fuctionality to support `0/1D` cases.  


### 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
2024-05-14 19:34:04 +03:00
alexlyulkov
03507e06b4
Merge pull request #25518 from alexlyulkov:al/fixed-gemm-openvino
Fixed OpenVINO gemm layer #25518

Fixed OpenVINO gemm layer
The problem was that our layer didn't properly handle all the possible gemm options in OpenVINO mode
Fixes #25472

### 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
2024-05-14 17:41:19 +03:00
Abduragim Shtanchaev
021e5184bc
Merge pull request #25567 from Abdurrahheem:ash/01D-einsum-test
0/1D Einsum Layer Test #25567

This PR introduces 0/1D test cases for Einsum layer.

TODO:
- Add support for 0D tensors to Einsum layer

### 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
2024-05-14 15:45:56 +03:00
Wanli
b637e3a66e
Merge pull request #25463 from WanliZhong:ocvface2YuNet
Change opencv_face_detector related tests and samples from caffe to onnx #25463

Part of https://github.com/opencv/opencv/issues/25314

This PR aims to change the tests related to opencv_face_detector from caffe framework to onnx. Tests in `test_int8_layer.cpp` and `test_caffe_importer.cpp` will be removed in https://github.com/opencv/opencv/pull/25323

### 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
- [ ] 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
2024-05-08 15:49:10 +03:00
Alexander Smorkalov
d8e18f4576 Made fcn-resnet50-12.onnx model optional. 2024-05-03 16:14:22 +03:00
Alexander Smorkalov
ac9a858377
Merge pull request #25524 from alexlyulkov:al/openvino-layers
Added more OpenVINO layers to dnn
2024-05-03 13:16:56 +03:00
Wanli
ed47cce1c5 change fcn8s-heavy-pascal tests from caffe to onnx 2024-05-03 00:15:09 +08:00
Alexander Lyulkov
f3f29fa62c Added more OpenVINO layers to dnn 2024-05-02 14:37:40 +03:00
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
Abduragim Shtanchaev
bbe86e6dea
Merge pull request #25480 from Abdurrahheem:ash/comf-denylist-reduce
Add logs of test failure to test_onnx_conformance_layer_filter_opencv_all_denylist.inl.hpp #25480

### Pull Request Readiness Checklist

This PR add logs to test failures to  `test_onnx_conformance_layer_filter_opencv_all_denylist.inl.hpp` and it continuation of #25442

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
2024-04-24 11:42:04 +03:00
Abduragim Shtanchaev
f08933b051
Merge pull request #25420 from Abdurrahheem:ash/01D-batchnorm
0/1D test for BatchNorm layer #25420

This PR introduces support for 0/1D inputs in `BatchNorm` layer.

### 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
2024-04-23 12:03:39 +03:00
Abduragim Shtanchaev
4f81d78c39
Merge pull request #25465 from Abdurrahheem:ash/parser-conf-denylist-reduce
Comments for parser denylist #25465

Relates to https://github.com/opencv/opencv/issues/21078

This PR is designed to figure out why the test in `test_onnx_conformance_layer_parser_denylist.inl.hpp` fails. Currently, conformance tests do not pass for the following reasons:

1. BOOL, INT(8, 16) types are not supported **(MAJOR)**
2. Some layers can not be created due to various reasons  **(MAJOR)**
3. Shape mismatches while creating layers  **(MAJOR)**
4. Some layers are expected to support dynamic parameter initialization  **(MAJOR)**
5. Some layers are expected to receive weight as inputs (no idea why that is needed)   **(MAJOR)**
6. Other unknown reasons

 **(MAJOR)** - These are the most frequently encountered reasons for test failure.

The style of comments is not consistent everywhere. Let's keep this PR without merging, just for our reference.
A couple of tests are commented on since they have passed on the MacOS platform.

### 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
2024-04-22 16:31:15 +03:00
Alexander Smorkalov
43d243dd0e Merge branch 4.x 2024-04-22 11:08:39 +03:00
Abduragim Shtanchaev
b009a63e6b
Merge pull request #25442 from Abdurrahheem:ash/comf-denylist-reduce
Conformance test denylist reduce #25442

Comment out all passing tests in `test_onnx_conformance_layer_filter_opencv_all_denylist.inl.hpp` file. 


### 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
2024-04-18 17:22:56 +03:00
Abdurrahheem
6b438835eb Constant layer 0/1D test. 2024-04-17 11:39:31 +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
db3e5620cd Merge branch 4.x 2024-04-16 17:28:18 +03:00
Abduragim Shtanchaev
869016d8b1
Merge pull request #25208 from Abdurrahheem:ash/0D-fullyConnected-test
Fully connected 0D test. #25208

This PR introduces parametrized `0/1D` input support test for `Fullyconnected` layer.

### 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
2024-04-15 09:15:36 +03:00
Alexander Smorkalov
ecbfc1bfd8
Merge pull request #25395 from susumu-iino:fix-dnn-plugin-build-win32
Fix dnn plugin build win32
2024-04-12 11:05:34 +03:00
Yuantao Feng
197626a5bf
Merge pull request #25387 from fengyuentau:complete-float16_t-renaming
Rename remaining float16_t for future proof #25387

Resolves comment: https://github.com/opencv/opencv/pull/25217#discussion_r1547733187.

`std::float16_t` and `std::bfloat16_t` are introduced since c++23: https://en.cppreference.com/w/cpp/types/floating-point.

### 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
2024-04-11 14:02:44 +03:00
Alexander Smorkalov
282c762ead Merge branch 4.x 2024-04-10 11:27:47 +03:00
Alexander Smorkalov
e4677fbf64
Merge pull request #25361 from hanliutong:rvv-f32
Further optimize fastDepthwiseConv for RISC-V Vector.
2024-04-09 16:04:02 +03:00
alexlyulkov
f454303f6a
Merge pull request #25241 from alexlyulkov:al/int64-padding
Added int support to padding layer #25241

Added int32 and int64 support to padding layer (CPU and CUDA).
ONNX parser doesn't convert non-zero padding value to float now.

### 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
- [ ] 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
2024-04-09 11:20:56 +03:00
Abdurrahheem
ab7ab7b6be Slice Layer 1D test. 2024-04-09 08:52:49 +03:00
ecchen
e63690a2d9 Add a shape checker for tflite models 2024-04-08 13:28:05 +00:00
Alexander Smorkalov
f2c3d4dfe3
Merge pull request #25369 from dkurt:resolve_valgrind_warnings
Resolve valgrind warnings
2024-04-08 12:48:59 +03:00
Abdurrahheem
a31f4f4040 git squash 2024-04-08 10:47:23 +03:00
Dmitry Kurtaev
bfd1504de3 Resolve valgrind warnings 2024-04-08 09:35:21 +03:00
Susumu IINO
a0b28f8b06 Add Definition "_USE_MATH_DEFINES" for dnn plugin on Win32 build 2024-04-07 21:08:09 +09:00
Liutong HAN
5be158a2b6 Further optimize fastDepthwiseConv for RVV. 2024-04-07 11:34:41 +08:00
Abduragim Shtanchaev
22b1b1edac
Merge pull request #25071 from Abdurrahheem:ash/1D-scatter
1D Scatter Layer Test #25071

This PR introduces parametrized test for `Scatter` layer to test its functionality for 1D arrays


### 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
2024-04-05 15:55:23 +03:00
Alexander Smorkalov
2e784bc7e6
Merge pull request #25330 from alexlyulkov:al/dnn-int64-more-tests
Added int tests for Const, Concat, ScatterND, NaryEltwise, Arg, Blank layers
2024-04-05 09:58:06 +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
Abdurrahheem
753e2c1dfa Added 1d tensors support to SoftMax layer. 2024-04-04 11:10:24 +03:00
Abduragim Shtanchaev
65074651a4
Merge pull request #25224 from Abdurrahheem:ash/0D-concat-test
Concat Layer 0/1D test #25224

This PR introduces parametrized `0/1D` input support test for `Concat` layer.

### 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
2024-04-04 10:36:00 +03:00
Alexander Lyulkov
b64ce1e7f1 Added tests for Const, Concat, ScatterND, NaryEltwise, Arg, Blanc 2024-04-03 18:41:53 +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
c1e2f16f91
Merge pull request #25225 from Abdurrahheem:ash/0d-expand-test
Expand 0D layer test
2024-04-03 09:53:46 +03:00
Dmitry Kurtaev
13c95efa74
Merge pull request #25312 from dkurt:dnn_hotfix_tflite
Ownership check in TFLite importer #25312

### Pull Request Readiness Checklist

resolves https://github.com/opencv/opencv/issues/25310

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 09:41:40 +03:00
Alexander Smorkalov
cb6d295f15 Merge branch 4.x 2024-04-02 16:39:54 +03:00
Abdurrahheem
eddace4d98 git squash 2024-04-01 17:22:39 +04:00
HAN Liutong
eba158fb0c
Merge pull request #25230 from hanliutong/rvv-conv
Optimize int8 layers in DNN modules by using RISC-V Vector intrinsic. #25230

This patch optimize 3 functions in the int8 layer by using RVV Native Intrinsic.

This patch was tested on QEMU using VLEN=128 and VLEN=256 on `./bin/opencv_test_dnn --gtest_filter="*Int8*"`;
On the real device (k230, VLEN=128), `EfficientDet_int8` in `opencv_perf_dnn` showed a performance improvement of 1.46x.

| Name of Test                               |  Original | optimized | Speed-up |
| ------------------------------------------ | -------- | ---------- | -------- |
| EfficientDet_int8::DNNTestNetwork::OCV/CPU | 2843.467 | 1947.013   | 1.46     |


### Pull Request Readiness Checklist

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

- [ ] I agree to contribute to the project under Apache 2 License.
- [ ] 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
- [ ] The PR is proposed to the proper branch
- [ ] 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.
- [ ] The feature is well documented and sample code can be built with the project CMake
2024-03-31 16:47:06 +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
Alexander Smorkalov
9fc4b61074
Merge pull request #25291 from dkurt:einsum_openvino
Einsum OpenVINO backend
2024-03-29 15:54:26 +03:00
Dmitry Kurtaev
cfa42e4338 Einsum OpenVINO backend 2024-03-29 14:29:45 +03:00
Dmitry Kurtaev
01dc010436
Merge pull request #25273 from dkurt:tflite_new_layers
TFLite new layers #25273

### Pull Request Readiness Checklist

resolves https://github.com/opencv/opencv/issues/25272, https://github.com/opencv/opencv/issues/24965

**Merge with extra**: https://github.com/opencv/opencv_extra/pull/1160

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 11:21:13 +03:00
Abduragim Shtanchaev
5319772a56
Merge pull request #25205 from Abdurrahheem:ash/0D-split-test
0D test for split layer #25205

This PR introduces parametrized `0/1D` input support test for `Split` layer.

### 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
2024-03-26 15:13:41 +03:00
Yuantao Feng
accf200408
Merge pull request #25238 from fengyuentau:optimized_const
dnn: avoid const layer forwarding in layer norm layer and attention layer #25238

While profiling ViTs with dnn, I found `ConstLayer` can take a proportion of the inference time, which is weird. This comes from the data copy during the inference of `ConstLayer`. There is a chance that we can improve the efficiency of data copying but the easiest and most convenient way is to avoid `ConstLayer`. This PR change the way how we handle constants in layer normalization layer and attention layer, which is storing in the layer blobs instead of making constant layers for them.

Checklists:

- [x] Backend compatibility in layer normalization layer.

### 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
2024-03-26 15:09:51 +03:00
alexlyulkov
f0323fdd1e
Merge pull request #25218 from alexlyulkov:al/int64-tile
Allowed int types in Tile and Reduce layers #25218

Allowed any Mat type in Tile layer.
Allowed int64 type in Reduce layer.

ONNX tests with int32 and int64 inputs will be added later in a separate PR


### 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
- [ ] 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
2024-03-26 14:00:35 +03:00
Alexander Smorkalov
a33de44b0b
Merge pull request #25212 from alexlyulkov:al/dnn-int64-scatter
Added int64 values support to scatter, scatterND and maxunpool layers
2024-03-26 13:52:28 +03:00
Alexander Smorkalov
fc34554475
Merge pull request #25184 from dkurt:avoid_extra_memset
Avoid extra memset
2024-03-25 13:07:49 +03:00
Yuantao Feng
025e7602b9
Merge pull request #25166 from fengyuentau:fix_cann_gemm
dnn (CANN): Fix incorrect shape of 1d bias in Gemm #25166

Gemm layer was refactored some time ago. Users found that the mobilenet example in https://github.com/opencv/opencv/wiki/Huawei-CANN-Backend does not work because of incorrect shape set for 1d bias in Gemm. This PR resolves this issue.

### 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
2024-03-25 09:47:28 +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
f8319de976
Added int support to CumSum layer (#25214)
* Added int support to CumSum layer

* Allowed int types in CumSum layer

---------

Co-authored-by: Alexander Lyulkov <alexander.lyulkov@opencv.ai>
2024-03-22 04:35:43 +03:00
Abduragim Shtanchaev
d188319b82
0D test for Reshape layer (#25206)
* reshape test for 0D

* fix comments according to PR
2024-03-22 03:59:08 +03:00
alexlyulkov
aa9e80b07b
Added native int64 indices support to gather layer (#25211)
Co-authored-by: Alexander Lyulkov <alexander.lyulkov@opencv.ai>
2024-03-22 03:43:20 +03:00
alexlyulkov
f2cf3c8890
Added int support to flatten, permute, reshape, slice layers (#25236)
Co-authored-by: Alexander Lyulkov <alexander.lyulkov@opencv.ai>
2024-03-22 03:39:42 +03:00
Oleg Pipikin
6da2ddcf0e Fix for OpenVINO 2024.0
Remove support OpenVINO lower than 2022.1 release
Remove legacy InferenceEngine wrappers
2024-03-18 15:05:50 +04:00
Alexander Lyulkov
d2d6869a26 Added int64 values support to scatter, scatterND and maxunpool layers 2024-03-13 15:40:07 +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
Dmitry Kurtaev
6a370ba9e7 Avoid extra memset in convolution initialization 2024-03-08 10:46:07 +03:00
Dmitry Kurtaev
98aed21dd4 Avoid copy of ONNX graph during import 2024-03-05 18:22:46 +03:00
Alexander Smorkalov
c6776ec136
Merge pull request #25159 from Kumataro:trial_to_fix_cv_check_24411
dnn: fix to iteration variable scope
2024-03-05 16:01:25 +03:00
Kumataro
216c6c3da1 dnn: fix to iteration variable scope 2024-03-05 18:33:56 +09:00
Maksim Shabunin
8cbdd0c833
Merge pull request #25075 from mshabunin:cleanup-imgproc-1
C-API cleanup: apps, imgproc_c and some constants #25075

Merge with https://github.com/opencv/opencv_contrib/pull/3642

* Removed obsolete apps - traincascade and createsamples (please use older OpenCV versions if you need them). These apps relied heavily on C-API
* removed all mentions of imgproc C-API headers (imgproc_c.h, types_c.h) - they were empty, included core C-API headers
* replaced usage of several C constants with C++ ones (error codes, norm modes, RNG modes, PCA modes, ...) - most part of this PR (split into two parts - all modules and calib+3d - for easier backporting)
* removed imgproc C-API headers (as separate commit, so that other changes could be backported to 4.x)

Most of these changes can be backported to 4.x.
2024-03-05 12:18:31 +03:00
Alexander Smorkalov
daa8f7dfc6 Partially back-port #25075 to 4.x 2024-03-05 12:15:39 +03:00
Laurent Berger
5fe3933346
Merge pull request #25120 from LaurentBerger:I25103
Fixed ReduceMean layer behaviour #25120

### 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.
- [ ] The feature is well documented and sample code can be built with the project CMake

a93c31e3c9/onnxruntime/core/providers/cpu/reduction/reduction_ops.cc (L433-L443)
2024-03-04 09:36:53 +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
CSBVision
e8582f2cf8 Update net_impl.cpp
See issue #25112
2024-03-01 14:56:00 +01:00
Alexander Smorkalov
010772b492 Extracted 1d test cases to reduce conflicts with 4.x. 2024-02-29 12:02:00 +03:00
Alexander Smorkalov
92b940792a
Merge pull request #25117 from Abdurrahheem:ash/scale-layer-1D-test
Scale layer 1d test
2024-02-29 11:32:13 +03:00
Alexander Smorkalov
a22130fbfa Merge branch 4.x 2024-02-28 18:49:05 +03:00
Yuantao Feng
5aa5c39210
Merge pull request #25076 from fengyuentau:improve_attention
dnn: try improving performance of Attention layer #25076

Checklist:

- [x] Use `Mat` over `Mat::zeros` for temporary buffer in forward
- [x] Use layer internal buffer over temporary Mat buffer
- [x] Try a single fastGemmBatch on the Q/K/V calculation

Performance:

Performance test case is `Layer_Attention.VisionTransformer/0`, which has input of shape {1, 197, 768}, weight of shape {768, 2304} and bias {2304}.

Data is in millisecond.

| | macOS 14.2.1, Apple M1 | Ubuntu 22.04.2, Intel i7 12700K |
| - | - | - |
| Current | 10.96 | 1.58 |
| w/ Mat | 6.27 | 1.41 |
| w/ Internals | 5.87 | 1.38 |
| w/ fastGemmBatch | 6.12 | 2.14 |


### 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
2024-02-28 16:47:08 +03:00
Abdurrahheem
161c402f02 seperated working scale layer 1d test. 2024-02-28 13:04:48 +04:00
Laurent Berger
3c712cf77d
Merge pull request #25100 from LaurentBerger:I25077
Fix issue #25077 #25100

Fixes https://github.com/opencv/opencv/issues/25077

### 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
2024-02-27 14:15:11 +03:00
Abduragim Shtanchaev
093ed08892
Merge pull request #24977 from Abdurrahheem:ash/primitive_1d_tests
Primitive 1D Tests #24977

This PR is designed to add tests for 1D inputs for layer, which is required after introducing 1d support in 5.x. Currently tests are written for following layers: 

- [x] `Add`, `Sub`
- [x]  `Product`, `Div`
- [x]  `Min`, `Max`
- [x] `Argmin`, `Argmax`
- [x] `Gather` 

This list is to be extended for more layer such `gemm`, `conv` etc.

### 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
2024-02-21 17:37:49 +03:00
Alexander Smorkalov
f084a229b4 Merge branch 4.x 2024-02-19 09:06:26 +03:00
Yuantao Feng
d4fd5157fa
Merge pull request #24980 from fengyuentau:on-fly-quantization-removal
dnn cleanup: On-fly-quantization removal #2498

On-fly-quantization is first introduced via https://github.com/opencv/opencv/pull/20228.
We decided to remove it but keep int8 layers implementation because on-fly-quantization
is less practical given the fact that there has been so many dedicated tools for model
quantization.

### 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
2024-02-16 18:21:45 +03:00