8808aaccff
Merge pull request #16658 from YashasSamaga:cuda4dnn-refactor-activations
...
cuda4dnn(activations, eltwise, scale_shift): refactor to reduce code duplication
* refactor activations
* refactor eltwise kernels
* move all functors to functors.hpp
* remove bias1 and scale1 kernels
2020-02-29 11:46:14 +03:00
333a767be4
Merge remote-tracking branch 'upstream/3.4' into merge-3.4
2020-02-28 18:34:37 +00:00
9c4b1d0a51
Merge pull request #16685 from YashasSamaga:cuda4dnn-fix-tests-pr16595
2020-02-27 20:42:45 +00:00
98b5fb4b9f
disable MaskRCNN test for CUDA_FP16
2020-02-28 15:44:37 +05:30
cc0066d38d
dnn(test): adjust check tolerance in Keypoints_face
2020-02-27 19:44:51 +03:00
5bbe116f89
Track Hetero execution for nGraph networks using ngraph::Function
2020-02-27 17:45:28 +03:00
45d073f889
Merge remote-tracking branch 'upstream/3.4' into merge-3.4
2020-02-26 20:09:03 +03:00
d8dea7896b
Merge pull request #16628 from dkurt:dnn_ngraph_custom_layers
...
* Custom layers with nGraph
* nGraph: multiple outputs from nodes
2020-02-26 17:51:18 +03:00
f48c84eaee
Merge pull request #16656 from alalek:issue_16655
2020-02-26 12:47:46 +00:00
a5d0c7b02c
Merge pull request #16650 from ashishkrshrivastava:cvdarknet
2020-02-25 12:57:11 +00:00
c2f5f5a202
dnn(test): configure filtering for 32-bit systems (part 2)
2020-02-24 18:18:33 +00:00
5e082ab852
resize tensor on reuse if required
2020-02-24 10:45:59 +05:30
fce6e7248e
Merge pull request #16629 from alalek:dnn_test_32bit
2020-02-23 17:09:31 +00:00
d54d01ca46
core(MatExpr): fix .type() bug
2020-02-23 17:05:05 +00:00
2b96a485e7
Darknet_io: Parsing for cost layer added
2020-02-23 21:06:48 +05:30
8eafddf211
Merge pull request #16647 from YashasSamaga:cuda4dnn-hotfix-i16568
2020-02-22 22:21:56 +00:00
1540ae340f
dnn(test): configure filtering for 32-bit systems
2020-02-22 17:35:26 +00:00
c23ab37355
fix weights rank assertion in InnerProductOp
2020-02-22 16:59:09 +05:30
01048e5603
Merge pull request #16616 from alalek:dnn_fix_input_shape
...
* dnn: fix processing of input shapes
- importer: avoid using of .setInput() => .setInputShape()
- setInput: shape limitation check (partial)
* dnn(test): test .setInput() in readNet()
2020-02-21 22:39:54 +03:00
102ef39a27
Merge pull request #16225 from berak:dnn_pose_estimation
...
dnn: small fix in pose estimation model
2020-02-21 22:37:23 +03:00
96b26dc8f4
Merge remote-tracking branch 'upstream/3.4' into merge-3.4
2020-02-20 19:47:27 +03:00
4fdf4d380c
dnn: small fix in pose estimation model
2020-02-20 17:08:55 +01:00
30331eef4b
Merge pull request #16595 from dkurt:dnn_ie_mask_rcnn
2020-02-20 12:50:27 +00:00
1f695c4532
Merge pull request #16161 from YashasSamaga:cuda4dnn-concat-fusion
...
cuda4dnn(concat): write outputs from previous layers directly into concat's output
* eliminate concat by directly writing to its output buffer
* fix concat fusion not happening sometimes
* use a whitelist instead of a blacklist
2020-02-20 15:43:05 +03:00
f3eef792eb
Enable Mask R-CNN with Inference Engine. Full coverage with nGraph
2020-02-20 10:13:40 +03:00
4b0d3316f6
Merge pull request #16617 from alalek:dnn_fix_caffe_importer
2020-02-19 10:57:27 +00:00
7ac7aca33b
dnn(caffe): fix net.input_dim handling in Caffe importer
2020-02-19 07:37:27 +00:00
1602a38fa9
Merge pull request #16572 from alalek:dnn_test_dldt_ir_v10
...
* dnn(test): test DLDT IRv10 model, drop old models
* dnn(test): don't expect bitexact results in DLDT IR tests
2020-02-18 17:57:46 +03:00
e970eccbf1
Merge pull request #16472 from l-bat:cp_vton
...
Add CP-VTON sample
* Support resize from PyTorch
* Add CP-VTON sample
* Fix downsampling
* Fix test
* Add model links
* Add default args
* Speed up resize
* Fix TOM link
* Add default args
* Fix comments
* Set aspect ratio for input
* Update links
* Check files exist
2020-02-17 22:29:37 +03:00
a6f3a21256
Merge pull request #16424 from czgdp1807:issue-16370
...
* fixed Split layer in ONNXImporter
* added test for fix of split layer
* fixed tests for Split layer
* applied reviews
* updated tests
* fixed paths in tests
2020-02-15 14:12:20 +03:00
f3237fdc6e
Merge remote-tracking branch 'upstream/3.4' into merge-3.4
2020-02-14 19:54:59 +03:00
9a4cafa319
Resolve #14566
2020-02-14 00:21:38 +03:00
0a91261c7f
dnn: turn off visibility workaround for OpenVINO 2020.1
2020-02-12 17:22:44 +03:00
d81a0da3e0
dnn: use OpenVINO 2020.1 defines
2020-02-12 17:21:08 +03:00
2a6637afdf
Merge pull request #16516 from alalek:dnn_dump_network
2020-02-11 16:22:32 +00:00
aa2777ed61
Merge remote-tracking branch 'upstream/3.4' into merge-3.4
2020-02-10 19:40:29 +03:00
db9f4436e0
Merge pull request #16473 from ashishkrshrivastava:opencvtf
2020-02-09 11:52:24 +03:00
cd53144ed3
commit: Corrected end tensor_content parsing for StridedSlice layer.
2020-02-09 06:43:23 +05:30
eb14f9a464
Merge pull request #16463 from alalek:core_strong_ptr_alignment
2020-02-08 19:45:43 +00:00
0a691f7840
Merge pull request #16529 from alalek:dnn_skip_failed_ngraph_tests
2020-02-08 18:53:10 +00:00
8ecfb59930
dnn(test): skip failed ngraph tests
2020-02-07 22:43:40 +00:00
bcc9946650
Merge pull request #16438 from ashishkrshrivastava:opencvc
2020-02-07 23:17:59 +03:00
d64529f6de
Added parsing for Connected and Dropout. Modified maxpool padding
2020-02-07 07:26:36 +05:30
ac0a14631d
dnn: eliminate MSVC warnings from ngraph.hpp
2020-02-06 19:53:49 +00:00
6eba1a4d44
dnn: auto network dump through parameter
2020-02-05 21:46:32 +00:00
fa4871b013
dnn: don't require setInput in .dump()
2020-02-05 21:28:07 +00:00
225566da7b
Merge remote-tracking branch 'upstream/3.4' into merge-3.4
2020-02-04 19:49:24 +03:00
005f38fb45
Fix dnn::ResizeLayer to manage varying input shapes
2020-02-04 09:06:17 +03:00
2ced568d34
Merge pull request #16220 from YashasSamaga:cuda4dnn-roi-pooling-test_fix-optim
2020-01-29 20:57:15 +00:00
a4bd7506a5
core: CV_STRONG_ALIGNMENT macro
...
Should be used to guard unsafe type casts of pointers
2020-01-29 18:44:17 +03:00
Yashas Samaga B L