- 11 2月, 2023 1 次提交
-
-
由 Yuantao Feng 提交于
Add GELU layer for vision transformers * add gelu and gelu approximation * drop setKernelParams
-
- 27 1月, 2023 1 次提交
-
-
由 Yuantao Feng 提交于
dnn: add layer normalization for vision transformers * add layer norm onnx parser, impl and tests * add onnx graph simplifier for layer norm expanded * handle the case when constants are of type Initializer * add test case for layer norm expanded with initializers * use CV_Assert & CV_CheckType in place of CV_Assert_N; use forward_fallback for OCL_FP16 * use const ref / ref in parameters of invoker::run; extract inner const if from nested loop; use size_t in place of ull * template hasBias * remove trailing whitespace * use pointer parameter with null check; move normSize division & mean_square division outside of loop; use std::max to ensure positive value before std::sqrt * refactor implementation, optimize parallel_for * disable layer norm expanded * remove the removal of layer norm optional outputs
-
- 29 11月, 2022 1 次提交
-
-
由 fengyuentau 提交于
-
- 17 10月, 2022 1 次提交
-
-
由 fengyuentau 提交于
-
- 08 10月, 2022 1 次提交
-
-
由 Alexander Alekhin 提交于
-
- 19 9月, 2022 1 次提交
-
-
由 Egor Smirnov 提交于
-
- 19 7月, 2022 1 次提交
-
-
由 rogday 提交于
Reimplementation of Element-wise layers with broadcasting support * init * semi-working initial version * add small_vector * wip * remove smallvec * add nary function * replace auto with Mat in lambda expr used in transform * uncomment asserts * autobuffer shape_buf & step_buf * fix a missing bracket * fixed a missing addLayer in parseElementWise * solve one-dimensional broadcast * remove pre_broadcast_transform for the case of two constants; fix missing constBlobsExtraInfo when addConstant is called * one autobuffer for step & shape * temporal fix for the missing original dimension information * fix parseUnsqueeze when it gets a 1d tensor constant * support sum/mean/min/max with only one input * reuse old code to handle cases of two non-constant inputs * add condition to handle div & mul of two non-constant inputs * use || instead of or * remove trainling spaces * enlarge buf in binary_forward to contain other buffer * use autobuffer in nary_forward * generate data randomly and add more cases for perf * add op and, or & xor * update perf_dnn * remove some comments * remove legacy; add two ONNX conformance tests in filter * move from cpu_denylist to all_denylist * adjust parsing for inputs>=2 Co-authored-by: Nfengyuentau <yuantao.feng@opencv.org.cn>
-
- 07 4月, 2022 1 次提交
-
-
由 zihaomu 提交于
-
- 18 3月, 2022 1 次提交
-
-
由 Zihao Mu 提交于
-
- 18 12月, 2021 1 次提交
-
-
由 Smirnov Egor 提交于
-
- 17 12月, 2021 1 次提交
-
-
由 Smirnov Egor 提交于
Add acos, acosh, asin, asinh, atan, atanh, cos, cosh, erf, hardswish, sin, sinh, softplus, softsign, tan layers
-
- 07 12月, 2021 1 次提交
-
-
由 Smirnov Egor 提交于
-
- 15 10月, 2021 1 次提交
-
-
由 Smirnov Egor 提交于
-
- 05 10月, 2021 1 次提交
-
-
由 Jebastin Nadar 提交于
dnn : int8 quantized layers support in onnx importer * added quantized layers support in onnx importer * added more cases in eltwise node, some more checks * added tests for quantized nodes * relax thresholds for failed tests, address review comments * refactoring based on review comments * added support for unsupported cases and pre-quantized resnet50 test * relax thresholds due to int8 resize layer
-
- 19 8月, 2021 1 次提交
-
-
由 SamFC10 提交于
-
- 18 8月, 2021 1 次提交
-
-
由 thezane 提交于
* Support cumsum layer for onnx * Add unit tests * Address review comments
-
- 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
-
- 01 3月, 2021 1 次提交
-
- 21 2月, 2021 1 次提交
-
-
由 SamFC10 提交于
-
- 19 5月, 2020 1 次提交
-
-
由 Liubov Batanina 提交于
Support FlowNet2 model * Support DataAugmentation layer * Fix warnings * Fix comments * Support Correlation layer * TEST * Support Correlation layer * Supported Accum and FlowWarp layers * Supported ChannelNorm layer * Supported Resample with inputs.size() > 1 * Fixed comments * Refactoring * Added tests * Add resample test * Added asserts in resize layer * Updated DataAugmentation layer * Update convolution layer * Refactoring * Fix data augmentation layer * Fix caffe importer * Fix resize * Switch to Mat ptr * Remove useless resize type * Used ResizeLayer in Accum * Split ChannelNormLayer * Delete duplicate assert * Add sample * Fix sample * Added colormap
-
- 04 4月, 2020 1 次提交
-
-
由 Dmitry Kurtaev 提交于
-
- 02 12月, 2019 1 次提交
-
-
由 Manjunath Bhat 提交于
* Added Swish and Mish activations * Fixed whitespace errors * Kernel implementation done * Added function for launching kernel * Changed type of 1.0 * Attempt to add test for Swish and Mish * Resolving type mismatch for log * exp from device * Use log1pexp instead of adding 1 * Added openCL kernels
-
- 01 12月, 2019 1 次提交
-
-
由 thebhatman 提交于
-
- 05 12月, 2018 1 次提交
-
-
由 Dmitry Kurtaev 提交于
-
- 07 9月, 2018 1 次提交
-
-
由 Hamdi Sahloul 提交于
-
- 04 9月, 2018 1 次提交
-
-
由 Alexander Alekhin 提交于
- differ from 3.4 branch
-
- 23 6月, 2018 1 次提交
-
-
由 Dmitry Kurtaev 提交于
-
- 22 6月, 2018 1 次提交
-
-
由 Dmitry Kurtaev 提交于
-
- 07 6月, 2018 1 次提交
-
-
由 David 提交于
* Added ResizeBilinear op for tf Combined ResizeNearestNeighbor and ResizeBilinear layers into Resize (with an interpolation param). Minor changes to tf_importer and resize layer to save some code lines Minor changes in init.cpp Minor changes in tf_importer.cpp * Replaced implementation of a custom ResizeBilinear layer to all layers * Use Mat::ptr. Replace interpolation flags
-
- 30 5月, 2018 1 次提交
-
-
由 Dmitry Kurtaev 提交于
-
- 20 12月, 2017 1 次提交
-
-
由 Dmitry Kurtaev 提交于
-
- 15 12月, 2017 1 次提交
-
-
由 Dmitry Kurtaev 提交于
-
- 08 12月, 2017 1 次提交
-
-
由 Dmitry Kurtaev 提交于
-
- 27 11月, 2017 1 次提交
-
-
由 Dmitry Kurtaev 提交于
-
- 11 10月, 2017 1 次提交
-
-
由 Dmitry Kurtaev 提交于
-
- 10 10月, 2017 2 次提交
-
-
由 AlexeyAB 提交于
-
由 Dmitry Kurtaev 提交于
-
- 06 10月, 2017 2 次提交
-
-
由 Dmitry Kurtaev 提交于
-
-
- 26 9月, 2017 1 次提交
-
-
由 Dmitry Kurtaev 提交于
-