|
|
|
|
name: PR:5.x
|
|
|
|
|
|
|
|
|
|
on:
|
|
|
|
|
pull_request:
|
|
|
|
|
branches:
|
|
|
|
|
- 5.x
|
|
|
|
|
|
|
|
|
|
jobs:
|
|
|
|
|
Ubuntu2004-ARM64:
|
|
|
|
|
uses: opencv/ci-gha-workflow/.github/workflows/OCV-PR-5.x-ARM64.yaml@main
|
|
|
|
|
|
|
|
|
|
Ubuntu2004-ARM64-Debug:
|
|
|
|
|
uses: opencv/ci-gha-workflow/.github/workflows/OCV-PR-5.x-ARM64-Debug.yaml@main
|
|
|
|
|
|
|
|
|
|
Ubuntu2004-x64:
|
|
|
|
|
uses: opencv/ci-gha-workflow/.github/workflows/OCV-PR-5.x-U20.yaml@main
|
|
|
|
|
|
|
|
|
|
Ubuntu2204-x64:
|
|
|
|
|
uses: opencv/ci-gha-workflow/.github/workflows/OCV-PR-5.x-U22.yaml@main
|
|
|
|
|
|
|
|
|
|
Ubuntu2004-x64-CUDA:
|
|
|
|
|
if: "${{ contains(github.event.pull_request.labels.*.name, 'category: dnn') }} || ${{ contains(github.event.pull_request.labels.*.name, 'category: dnn (onnx)') }}"
|
|
|
|
|
uses: opencv/ci-gha-workflow/.github/workflows/OCV-PR-5.x-U20-Cuda.yaml@main
|
|
|
|
|
|
|
|
|
|
Windows10-x64:
|
|
|
|
|
uses: opencv/ci-gha-workflow/.github/workflows/OCV-PR-5.x-W10.yaml@main
|
|
|
|
|
|
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
10 months ago
|
|
|
# Vulkan configuration disabled as Vulkan backend for DNN does not support int/int64 for now
|
|
|
|
|
# Details: https://github.com/opencv/opencv/issues/25110
|
|
|
|
|
# Windows10-x64-Vulkan:
|
|
|
|
|
# uses: opencv/ci-gha-workflow/.github/workflows/OCV-PR-5.x-W10-Vulkan.yaml@main
|
|
|
|
|
|
|
|
|
|
macOS-ARM64:
|
|
|
|
|
uses: opencv/ci-gha-workflow/.github/workflows/OCV-PR-5.x-macOS-ARM64.yaml@main
|
|
|
|
|
|
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
10 months ago
|
|
|
# macOS-ARM64-Vulkan:
|
|
|
|
|
# uses: opencv/ci-gha-workflow/.github/workflows/OCV-PR-5.x-macOS-ARM64-Vulkan.yaml@main
|
|
|
|
|
|
|
|
|
|
macOS-x64:
|
|
|
|
|
uses: opencv/ci-gha-workflow/.github/workflows/OCV-PR-5.x-macOS-x86_64.yaml@main
|
|
|
|
|
|
|
|
|
|
iOS:
|
|
|
|
|
uses: opencv/ci-gha-workflow/.github/workflows/OCV-PR-5.x-iOS.yaml@main
|
|
|
|
|
|
|
|
|
|
Android:
|
|
|
|
|
uses: opencv/ci-gha-workflow/.github/workflows/OCV-PR-5.x-Android.yaml@main
|
|
|
|
|
|
|
|
|
|
TIM-VX:
|
|
|
|
|
uses: opencv/ci-gha-workflow/.github/workflows/OCV-timvx-backend-tests-4.x.yml@main
|
|
|
|
|
|
|
|
|
|
docs:
|
|
|
|
|
uses: opencv/ci-gha-workflow/.github/workflows/OCV-PR-5.x-docs.yaml@main
|
|
|
|
|
|
|
|
|
|
Linux-RISC-V-Clang:
|
|
|
|
|
uses: opencv/ci-gha-workflow/.github/workflows/OCV-PR-5.x-RISCV.yaml@main
|
