c24f10d647
Merge pull request #10268 from dkurt:fix_scale_layer
2017-12-08 18:46:50 +00:00
e307065c8e
Scale layer in case of 2D inputs
2017-12-08 17:34:59 +03:00
f2070c9f5d
Merge pull request #10255 from dkurt:dnn_roi_pooling
2017-12-08 11:20:07 +00:00
17dcf0e82d
ROIPooling layer
2017-12-07 19:04:38 +03:00
ef0650179b
Fix conv/deconv/fc layers FLOPS computation
2017-12-07 11:42:04 +03:00
6074f92d48
Merge pull request #10228 from pengli:dnn_new
2017-12-06 15:50:12 +00:00
59cbaca4d3
detection_output layer ocl implementation
...
Signed-off-by: Li Peng <peng.li@intel.com >
2017-12-06 22:35:59 +08:00
66feea6cac
region layer ocl implementation
...
Signed-off-by: Li Peng <peng.li@intel.com >
2017-12-07 02:26:46 +08:00
7707c9bfba
reorg layer ocl implementation
...
Signed-off-by: Li Peng <peng.li@intel.com >
2017-12-07 02:26:46 +08:00
85b1c4060c
support axis in concat layer ocl path
...
Signed-off-by: Li Peng <peng.li@intel.com >
2017-12-07 02:26:46 +08:00
07bec6bdcd
reshape layer ocl implementation
...
Signed-off-by: Li Peng <peng.li@intel.com >
2017-12-07 02:26:40 +08:00
7b7033ac60
permute layer ocl implementation
...
Signed-off-by: Li Peng <peng.li@intel.com >
2017-12-05 22:10:05 +08:00
bbbec300a6
nn.BatchNormalization and nn.Dropout layers from Torch
2017-12-04 12:57:21 +03:00
cc2ee923e4
Merge pull request #10164 from pengli:dnn
2017-11-29 12:05:10 +00:00
1f465a0ef9
dnn(ocl4dnn): fuseLayer() use umat_input/outputBlobs for OpenCL target
...
Also, fix bug when use OPENCL target but no OpenCL runtime
Signed-off-by: Wu Zhiwen <zhiwen.wu@intel.com >
2017-11-27 22:25:53 +08:00
99ed085752
Update PriorBox layer
2017-11-27 16:47:20 +03:00
13f374660f
dnn(ocl4dnn): drop unused batch_size_ in pooling
2017-11-23 20:46:56 +00:00
e34b64c979
dnn(ocl4dnn): refactor pooling OpenCL calls
2017-11-23 20:46:44 +00:00
f071a48ec7
Merge pull request #10143 from pengli:ocl4dnn
2017-11-23 18:47:14 +00:00
107582c767
Merge pull request #9996 from dkurt:dnn_multiple_inputs
2017-11-23 18:22:37 +00:00
636d6368ee
use OutputArrayOfArrays in net forward interface
...
It allows umat buffers used in net forward interface
Signed-off-by: Li Peng <peng.li@intel.com >
2017-11-24 02:19:10 +08:00
04edc8fe3a
cleanup ocl4dnn spatial convolution kernels
...
remove unused macros and half definition macros,
also remove unused ocl::Queue
Signed-off-by: Li Peng <peng.li@intel.com >
2017-11-24 02:19:10 +08:00
49a5280198
Merge pull request #10139 from alalek:dnn_rename_caffe_proto_package
2017-11-23 14:10:42 +00:00
f37f4cf3b4
Merge pull request #9994 from r2d3:dnn_memory_load
2017-11-22 18:15:00 +00:00
e7d62d6ef3
Merge pull request #10126 from alalek:dnn_issue_10125
2017-11-22 18:03:51 +00:00
1c88a566e0
dnn: rename caffe protobuf package
2017-11-22 18:34:07 +03:00
9db5cbf9a4
dnn: sync output/internals blobs back
2017-11-22 14:00:58 +03:00
f8ad289311
Merge pull request #10092 from alalek:dnn_rename_caffe_proto
2017-11-22 08:16:20 +00:00
0f34628af7
dnn: drop OpenCL code path for DetectionOutputLayer
...
getUMat()/getMat() calls are scope based. Results of these calls can't be
stored somewhere for future usage.
2017-11-21 17:28:42 +03:00
438e456ce9
Merge pull request #10113 from wzw-intel:fusion
2017-11-20 18:13:33 +00:00
f6d927ef3b
dnn: avoid conflicts with original caffe.proto
...
rename caffe.proto => opencv-caffe.proto
2017-11-20 19:04:00 +03:00
f723cede2e
add loading TensorFlow/Caffe net from memory buffer
...
add a corresponding test
2017-11-20 16:28:22 +01:00
6c5dd5cf6d
Replace caffe::NormalizedBBox to local structure
2017-11-20 18:03:31 +03:00
45d11dde57
dnn(ocl4dnn): add fusion support for Power activation and eltwise add
...
Signed-off-by: Wu Zhiwen <zhiwen.wu@intel.com >
2017-11-20 14:58:53 +08:00
394101d6ed
dnn(ocl4dnn): Fix relu fusion bug
...
Incorrect type of negative_slope result in this bug.
Also and OCL test for darknet to validate this patch.
Signed-off-by: Wu Zhiwen <zhiwen.wu@intel.com >
2017-11-17 16:21:56 +08:00
88e6daa315
dnn(ocl4dnn): Fix wrong measurement for tuning time
...
convolution kernel use default queue to run, so that ocl::Timer
, to measure the kernel run time, should use the default queue too.
Also remove useless parameter for convolve()
Signed-off-by: Wu Zhiwen <zhiwen.wu@intel.com >
2017-11-16 13:09:57 +08:00
55260a8d3c
reshape mat before doing computation in fc layer
...
Signed-off-by: Li Peng <peng.li@intel.com >
2017-11-13 09:29:50 +08:00
bafdc44d37
Merge pull request #10061 from Sahloul:dnn_torch_fix
2017-11-10 05:05:52 +00:00
8a3a75cc16
Merge pull request #9882 from pengli:ocl4dnn
2017-11-09 18:54:43 +00:00
06bda58a2c
DNN Torch - workaround when torch importer is disabled
2017-11-10 00:44:06 +09:00
8f99083726
Add new layer forward interface
...
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 >
2017-11-09 15:59:39 +08:00
97181a90ba
dnn(ocl4dnn/conv): bailout on missing kernel configuration
2017-11-07 17:02:17 +03:00
6e4f9433d0
Merge pull request #9998 from alalek:ocl_fix_dnn_softmax_9991
2017-11-03 09:16:39 +00:00
20a2dc6ac5
Fix multiple inputs models from Caffe.
...
Fixed Concat optimization.
2017-11-02 18:55:08 +03:00
bacc96f4e8
dnn(ocl): fix softmax global/local size consistency
2017-11-02 17:08:40 +03:00
14af2a0c0c
Fixed Halide's copy_to_device invocation
2017-11-01 14:01:54 +03:00
bc348eb8ab
Merge pull request #9963 from dkurt:fix_caffe_shrinker
2017-10-31 12:27:19 +00:00
e1ebc4e991
Specify layer types for Caffe FP32->FP16 weights converter
2017-10-31 12:31:40 +03:00
03cefa7bfe
Set zero confidences in case of no detections
2017-10-30 10:17:57 +03:00
e0e40405ed
Merge pull request #9847 from wzw-intel:ocl4dnn_fusion
2017-10-27 13:59:46 +00:00
Vadim Pisarevsky
Dmitry Kurtaev
Alexander Alekhin
Li Peng
Wu Zhiwen
Alexander Alekhin
David Geldreich
Hamdi Sahloul