- 24 8月, 2021 2 次提交
-
-
由 Anatoliy Talamanov 提交于
[G-API] Extend compileStreaming to support different overloads * Make different overloads * Order python compileStreaming overloads * Fix compileStreaming bug * Replace gin -> descr_of * Set error message * Fix review comments * Use macros for pyopencv_to GMetaArgs * Use GAPI_PROP_RW * Not split Prims python stuff
-
由 Nicolai Behmann 提交于
* Added exposure and gain props, maximized pixel clk * removed pixel clock maximization pixel clock maximization is not suitable for all use cases, so I removed it from PR.
-
- 22 8月, 2021 1 次提交
-
-
由 Alexander Alekhin 提交于
-
- 20 8月, 2021 2 次提交
-
-
由 rogday 提交于
fix ONNXImporter diagnostic mode layer registration issue * fix layer registration, thread unsafe access and align the behavior of DNN_DIAGNOSTICS_RUN between onnx and tf importers * move skipModelInput * print all missing layers * address TF issue
-
由 Alexander Alekhin 提交于
-
- 19 8月, 2021 2 次提交
-
-
由 Vincent Rabaud 提交于
The two argument versions has been deprecated, cf https://developers.google.com/protocol-buffers/docs/reference/cpp/google.protobuf.io.coded_stream
-
由 SamFC10 提交于
-
- 18 8月, 2021 4 次提交
-
-
由 Anatoliy Talamanov 提交于
-
由 Anatoliy Talamanov 提交于
[G-API] Prohibit setPrecision & preprocessing for importedNetworks * Prohibit preprocessing for imported networks * Fix typo input_names -> output_names * Move setBlob logic to separate function * Change comment
-
由 Sergey Ivanov 提交于
G-API: oneVPL (simplification) source base commit * oneVPL source initial * Fix compilation * Fix compilation path * Fix NO VPL compile * Fix unused vars * Fix unused vars in example * Simplify oneVPL search: no custom path & download * Fix standalone GAPI * Apply comments
-
由 thezane 提交于
* Support cumsum layer for onnx * Add unit tests * Address review comments
-
- 17 8月, 2021 1 次提交
-
-
由 zyp 提交于
* videoio/gstreamer: Add support for GRAY16_LE. * videoio/gstreamer: added BGRA/BGRx support Co-authored-by: NMaksim Shabunin <maksim.shabunin@gmail.com>
-
- 16 8月, 2021 1 次提交
-
-
由 Smirnov Egor 提交于
-
- 14 8月, 2021 1 次提交
-
-
由 Iyad Ahmed 提交于
* VideoCapture add open/read timeout params to FFMPEG backend * Fix wrong enum name * Fix wrong enum name
-
- 13 8月, 2021 2 次提交
-
-
由 Julia Bareeva 提交于
* Support activations(Sigmoid, Tanh) for LSTM * fix warning
-
由 Iyad Ahmed 提交于
* VideoCapture timeout set/get * Common formatting for enum values * Fix enum values wrongly in videoio.hpp * Define timeout enum values in public api and align with master
-
- 12 8月, 2021 4 次提交
-
-
由 JIANG Yichen 提交于
The algorithm is based on Hannun's paper: First-Pass Large Vocabulary Continuous Speech Recognition using Bi-Directional Recurrent DNNs
-
由 AleksandrPanov 提交于
-
由 Daniel Playfair Cal 提交于
docs(core/ocl): clarify ownership of arguments passed into OpenCL related functions * docs(core/ocl): clarify ownership in OpenCLExecutionContext::create Although it is technically true that OpenCLExecutionContext::create calls `clRetainContext` on its context argument, it is misleading because it does not increase the reference count overall. Clarify that the ownership of one reference of the passed context and device is taken. * docs(core/ocl): document ownership transfer in ocl::Device::fromHandle
-
由 AleksandrPanov 提交于
-
- 11 8月, 2021 3 次提交
-
-
由 utibenkei 提交于
-
由 Hamdi Sahloul 提交于
-
由 HAN Liutong 提交于
Optimization of DNN using native RISC-V vector intrinsics. * Use RVV to optimize fastGEMM (FP32) in DNN. * Use RVV to optimize fastGEMM1T in DNN. * Use RVV to optimize fastConv in DNN. * Use RVV to optimize fastDepthwiseConv in DNN. * Vectorize tails using vl. * Use "vl" instead of scalar to handle small block in fastConv. * Fix memory access out of bound in "fastGEMM1T". * Remove setvl. * Remove useless initialization. * Use loop unrolling to handle tail part instead of switch.
-
- 10 8月, 2021 2 次提交
-
-
由 AleksandrPanov 提交于
-
由 Saikat Nanda 提交于
-
- 09 8月, 2021 2 次提交
-
-
由 Smirnov Egor 提交于
-
由 SamFC10 提交于
-
- 07 8月, 2021 1 次提交
-
-
由 Julia Bareeva 提交于
* Add initialization and inference for GRU layer * fix issues found on review
-
- 06 8月, 2021 3 次提交
-
-
由 Anatoliy Talamanov 提交于
[G-API] Expand PyParams to support constInput * Wrap constInputs to python * Wrap cfgNumRequests * Fix alignment * Move macro to the line above
-
由 Anatoliy Talamanov 提交于
[G-API] Support postprocessing for not argmaxed outputs * Support postprocessing for not argmaxed outputs * Fix typo * Add assert * Remove static cast * CamelCast to snake_case * Fix windows warning * Add static_cast to uint8_t * Add const to variables
-
由 Maxim Pashchenkov 提交于
-
- 05 8月, 2021 4 次提交
-
-
由 Julia Bareeva 提交于
Add Python's test for LSTM layer * Add Python's test for LSTM layer * Set different test threshold for FP16 target * rename test to test_input_3d Co-authored-by: NJulie Bareeva <julia.bareeva@xperience.ai>
-
由 Alexander Alekhin 提交于
- unexpected pkg-config module (we should not use host binary) - bump cmake_minimum_required to 3.5 in toolchain files
-
由 Anatoliy Talamanov 提交于
[G-API] Support FP16 input precision for IE backend * Support fp16 input precision IE backend * Add support to wrapIE
-
由 Alexander Smorkalov 提交于
-
- 04 8月, 2021 2 次提交
-
-
由 Duong Dac 提交于
-
由 AleksandrPanov 提交于
-
- 02 8月, 2021 1 次提交
-
-
由 Dmitry Budnikov 提交于
Remove explicit PNet resizes from MTCNN graph * remove PNet resizes * address comment from Ruslan
-
- 01 8月, 2021 1 次提交
-
-
由 Vadim Levin 提交于
-
- 30 7月, 2021 1 次提交
-
-
由 Smirnov Egor 提交于
-