ae6fabc6fe
dnn(ocl): drop CL_KERNEL_PREFERRED_WORK_GROUP_SIZE_MULTIPLE check
...
- it is a hint and it should not block kernel execution
2021-08-30 20:40:14 +00:00
4c05a697fa
Merge remote-tracking branch 'upstream/3.4' into merge-3.4
2021-08-28 21:30:28 +00:00
38d0063c36
Do not use deprecated ReleaseCleared in protobuf library.
...
This is to make code work with protobuf arenas for memory
management (ReleaseCleared is incompatible).
The cleaning of the memory is also simpler.
2021-08-26 15:36:22 +02:00
6fbfc58602
Merge remote-tracking branch 'upstream/3.4' into merge-3.4
2021-08-21 17:25:18 +00:00
77a5c43d50
Merge pull request #20586 from alalek:issue_20585
2021-08-21 17:22:58 +00:00
f28e4b86fb
dnn(ocl): fix top initialization in verifyResult
2021-08-21 16:04:13 +00:00
6801dd043d
Merge pull request #20494 from rogday:onnx_diagnostic_fix
...
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
2021-08-20 14:43:47 +00:00
a9817e9127
Merge pull request #20556 from rogday:onnx_split_sum_fix
2021-08-20 08:10:18 +00:00
9cfa84313c
Use the one argument version of SetTotalBytesLimit.
...
The two argument versions has been deprecated, cf
https://developers.google.com/protocol-buffers/docs/reference/cpp/google.protobuf.io.coded_stream
2021-08-19 14:31:29 +02:00
fa90e14b06
int8 layers and 8-bit quantization support
2021-08-19 09:56:47 +05:30
fe625a558e
fix hasDynamicShapes for batch_size and fix axis selection in Scale layer
2021-08-18 19:22:24 +03:00
210bfaf8d6
Merge pull request #20483 from thezane:support-cumsum-layer-for-onnx
...
* Support cumsum layer for onnx
* Add unit tests
* Address review comments
2021-08-17 20:09:25 +03:00
9ef41f68fb
fix Split partial sum
2021-08-16 15:44:54 +03:00
05d733e707
Merge pull request #20524 from yichenj:dnn_text_recognition_enhance
2021-08-15 12:30:25 +00:00
0c01cf7c85
Merge remote-tracking branch 'upstream/3.4' into merge-3.4
2021-08-14 18:24:00 +00:00
cfb36443fb
Merge pull request #20506 from JulieBar:lstm_activations
...
* Support activations(Sigmoid, Tanh) for LSTM
* fix warning
2021-08-13 15:41:00 +03:00
9d3826c676
Merge pull request #20525 from SamFC10:fix-prior-variances
2021-08-13 10:06:55 +00:00
955cf35d5f
Implement ctc prefix beam search decode for TextRecognitionModel.
...
The algorithm is based on Hannun's paper: First-Pass Large Vocabulary
Continuous Speech Recognition using Bi-Directional Recurrent DNNs
2021-08-12 20:33:31 +08:00
aaca4987c9
Merge pull request #20287 from hanliutong:dev-rvv-0.10
...
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.
2021-08-11 01:16:03 +03:00
739ff84732
add Max layer to TFImporter
2021-08-09 14:01:51 +03:00
2a177052de
fix bug in prior-box variances
2021-08-09 12:08:55 +05:30
424eaba4c5
Merge remote-tracking branch 'upstream/3.4' into merge-3.4
2021-08-07 17:25:06 +00:00
e1cafa3834
Merge pull request #20442 from JulieBar:gru_layer
...
* Add initialization and inference for GRU layer
* fix issues found on review
2021-08-07 10:07:37 +03:00
633fedaa96
Merge pull request #20480 from JulieBar:lstm_pytest
...
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: Julie Bareeva <julia.bareeva@xperience.ai >
2021-08-05 18:13:17 +03:00
907743eee7
Merge remote-tracking branch 'upstream/3.4' into merge-3.4
2021-07-30 14:50:36 +00:00
27392f832d
reimplement onnx refactor for master
2021-07-30 13:00:13 +03:00
cff0168f3a
Merge pull request #20453 from rogday:onnx_importer_fix
...
Split layer dispatch into functions in ONNXImporter
* split layer dispatch into functions
* fixes
* identation and comment fixes
* fix constness
2021-07-28 18:06:24 +03:00
f4d6a3ec4e
Merge remote-tracking branch 'upstream/3.4' into merge-3.4
2021-07-24 15:34:58 +00:00
4e5699fa71
Merge pull request #20450 from JulieBar:lstm_inside
...
Support non-zero hidden state for LSTM
* fully support non-zero hidden state for LSTM
* check dims of hidden state for LSTM
* fix failed test Test_Model.TextRecognition
* add new tests for LSTM w/ non-zero hidden params
Co-authored-by: Julie Bareeva <julia.bareeva@xperience.ai >
2021-07-23 17:11:50 +03:00
024b43ca06
implement asymmetric padding for conv2d, max_pool and conv2d_backprop_input
2021-07-22 16:58:40 +03:00
b61a55eebf
Merge pull request #20402 from rogday:tf_diag_dummy
2021-07-16 15:44:29 +00:00
c30078c5a3
add NotImplemented layer
2021-07-16 15:39:54 +03:00
39b91c97f0
Merge remote-tracking branch 'upstream/3.4' into merge-3.4
2021-07-16 10:35:42 +00:00
8334ee18e6
Merge pull request #20394 from SamFC10:conv-asymmetric-pads
2021-07-16 10:33:42 +00:00
96d35f7c54
Fix convolution asymmetric padding bug in onnx importer
2021-07-16 09:39:41 +05:30
fbde0c6c96
dnn(ie): fix handling of 1D and non-32F outputs of InferenceEngine
2021-07-15 21:47:05 +00:00
602e7c83e2
dnn(test): add extra IR models, more checks in IE testing code
2021-07-15 21:47:05 +00:00
bc210b292b
dnn(test): backport test_ie_models.cpp from 4.5.3
2021-07-15 00:05:02 +00:00
9e42e04b4a
Merge remote-tracking branch 'upstream/3.4' into merge-3.4
2021-07-10 13:01:03 +00:00
167a12028d
Merge pull request #20374 from cesarpgouveia:bugfix/fix_load_onnxModel_debug
...
* Fix bug while loading onnx model in debug
* dnn: fix other .at using
Co-authored-by: Alexander Alekhin <alexander.a.alekhin@gmail.com >
2021-07-09 18:21:56 +00:00
821fae0d94
Merge remote-tracking branch 'upstream/3.4' into merge-3.4
2021-07-03 00:30:58 +00:00
0f2f966a91
Merge pull request #20345 from mitruska:update_ngraph_normalizel2
2021-07-02 23:37:03 +00:00
18dbac203f
Use explicit version of ngraph NormalizeL2
2021-07-02 21:33:05 +00:00
8d1f254dcc
java: force using of 'Ptr<>' for OpenCV classes
...
backport of commit: e5841d3126
2021-07-02 21:20:08 +00:00
e5841d3126
java: force using of 'Ptr<>' for OpenCV classes
2021-07-02 21:13:49 +00:00
8fad85edda
Merge remote-tracking branch 'upstream/3.4' into merge-3.4
2021-07-01 10:52:31 +00:00
b699fe7a9d
Merge pull request #20335 from SamFC10:concat-const-input
2021-07-01 10:25:35 +00:00
5b8c10f2f8
modified onnx importer to concat const input blobs
2021-07-01 10:58:31 +05:30
24983f62e2
Merge pull request #20325 from alalek:dnn_openvino_2021.4.0
2021-06-30 23:58:26 +00:00
f2057ce1ab
dnn(ie): replace deprecated calls
2021-06-30 22:30:15 +00:00
Alexander Alekhin
Vincent Rabaud
rogday
SamFC10
thezane
Julia Bareeva
JIANG Yichen
HAN Liutong
César Gouveia
mitruska
Alexander Alekhin