- 14 Jun, 2019 1 commit
-
-
Dmitry Kurtaev authored
* Remove Inference Engine 2018R3 and 2018R4 * Fix 2018R5
-
- 08 Jun, 2019 1 commit
-
-
Lubov Batanina authored
* Support Slice layer in ONNX importer * Add IE support * Fix ONNX importer * Fix Slice
-
- 27 May, 2019 1 commit
-
-
Dmitry Kurtaev authored
-
- 17 Jan, 2019 1 commit
-
-
Dmitry Kurtaev authored
-
- 15 Nov, 2018 1 commit
-
-
Alexander Alekhin authored
-
- 26 Sep, 2018 1 commit
-
-
Dmitry Kurtaev authored
* Remove isIntel check from deep learning layers * Remove fp16->fp32 fallbacks where it's not necessary * Fix Kernel::run to prevent localsize > globalsize
-
- 06 Sep, 2018 1 commit
-
-
Dmitry Kurtaev authored
* Remove a forward method in dnn::Layer * Add a test * Fix tests * Mark multiple dnn::Layer::finalize methods as deprecated * Replace back dnn's inputBlobs to vector of pointers * Remove Layer::forward_fallback from CV_OCL_RUN scopes
-
- 01 Aug, 2018 1 commit
-
-
Dmitry Kurtaev authored
-
- 05 Jul, 2018 1 commit
-
-
Dmitry Kurtaev authored
-
- 09 Jun, 2018 1 commit
-
-
Dmitry Kurtaev authored
-
- 16 May, 2018 1 commit
-
-
Li Peng authored
Signed-off-by:
Li Peng <peng.li@intel.com>
-
- 27 Apr, 2018 1 commit
-
-
Alexander Alekhin authored
to avoid accessing of 'p[-1]' (static code analysers dislike this)
-
- 28 Mar, 2018 1 commit
-
-
Alexander Alekhin authored
-
- 01 Mar, 2018 2 commits
-
-
Alexander Alekhin authored
-
Alexander Alekhin authored
-
- 06 Feb, 2018 1 commit
-
-
Li Peng authored
Signed-off-by:
Li Peng <peng.li@intel.com>
-
- 31 Jan, 2018 1 commit
-
-
Dmitry Kurtaev authored
-
- 29 Jan, 2018 1 commit
-
-
Li Peng authored
Signed-off-by:
Li Peng <peng.li@intel.com>
-
- 09 Nov, 2017 1 commit
-
-
Li Peng authored
Add layer forward interface with InputArrayOfArrays and OutputArrayOfArrays parameters, it allows UMat buffer to be processed and transferred in the layers. Signed-off-by:
Li Peng <peng.li@intel.com>
-
- 27 Oct, 2017 1 commit
-
-
- 02 Oct, 2017 1 commit
-
-
Dmitry Kurtaev authored
-
- 26 Sep, 2017 1 commit
-
-
Dmitry Kurtaev authored
-
- 28 Jun, 2017 2 commits
-
-
Alexander Alekhin authored
-
Vadim Pisarevsky authored
* another round of dnn optimization: * increased malloc alignment across OpenCV from 16 to 64 bytes to make it AVX2 and even AVX-512 friendly * improved SIMD optimization of pooling layer, optimized average pooling * cleaned up convolution layer implementation * made activation layer "attacheable" to all other layers, including fully connected and addition layer. * fixed bug in the fusion algorithm: "LayerData::consumers" should not be cleared, because it desctibes the topology. * greatly optimized permutation layer, which improved SSD performance * parallelized element-wise binary/ternary/... ops (sum, prod, max) * also, added missing copyrights to many of the layer implementation files * temporarily disabled (again) the check for intermediate blobs consistency; fixed warnings from various builders
-
- 26 Jun, 2017 1 commit
-