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

modules/dnn/perf/perf_convolution3d.cpp

@@ -155,9 +155,17 @@ PERF_TEST_P_(Conv3D, conv3d)
     Mat output = net.forward();
 
     MatShape netInputShape = shape(input);
+    cv::dnn::MatType netInputType = input.depth();
+
+    bool fp16 = false;
+#ifdef HAVE_OPENCL
+    fp16 = ocl::Device::getDefault().isExtensionSupported("cl_khr_fp16");
+#endif
+    if (netInputType == CV_32F && fp16 && targetId == DNN_TARGET_OPENCL_FP16)
+        netInputType = CV_16F;
     size_t weightsMemory = 0, blobsMemory = 0;
-    net.getMemoryConsumption(netInputShape, weightsMemory, blobsMemory);
-    int64 flops = net.getFLOPS(netInputShape);
+    net.getMemoryConsumption(netInputShape, netInputType, weightsMemory, blobsMemory);
+    int64 flops = net.getFLOPS(netInputShape, netInputType);
     CV_Assert(flops > 0);
 
     std::cout