- 04 3月, 2020 1 次提交
-
-
由 HappyAngel 提交于
* add grid sampler * reset act * fix conflict and readme, test=develop * fix ios v8 run error * fix grid_sampler compute error. test=develop * fix exp act run error, test=develop * fix format, test=develop
-
- 03 3月, 2020 2 次提交
-
-
由 Yuan Shuai 提交于
-
由 HappyAngel 提交于
* fix leakyrelu and tanh compute error, test=develop * delete extra file, test=develop * reset act * fix conflict and readme, test=develop * fix ios run error, test=develop
-
- 02 3月, 2020 1 次提交
-
-
由 Yuan Shuai 提交于
* [LITE][OPENCL] Support video-sr feature using OpenCL FP16 Image. test=develop * optimize image2d_to_buffer_with_post255. test=develop * add def debug in cl kernel. test=develop * remove conv image code in conv buffer. test=develop
-
- 28 2月, 2020 2 次提交
-
-
由 mapingshuo 提交于
* add sequence_conv op and arm kernel * add test, test=develop * test=develop * test=develop * test=develop * test=develop * test=develop * test=develop * test=develop * test=develop * test=develop * test=develop * test=develop * test=develop * test=develop * test=develop * modify code style. test=develop * fix ut, test=develop * delete unused code, test=develop
-
由 xiebaiyuan 提交于
-
- 27 2月, 2020 2 次提交
-
-
由 Yuan Shuai 提交于
* replace vlog with log in pool, add each run duration print in test. test=develop * change layout file path. test=develop * fix act, layout image kernel. test=develop * fix spell error. test=develop * remove clfinish in act, concat, layout, nearest_interp. test=develop * add RELU macro define in fc opencl kernel. test=develop * add cpu_ref print in activation opencl kernel.test=develop * fix layout ut. test=develop * replace log with vlog. test=develop * fix get output. test=develop
-
由 xiaogang 提交于
* feat: add lstm op && kernel test=develop
-
- 26 2月, 2020 2 次提交
-
-
由 Jiaying Zhao 提交于
* [Lite][OpenCL]Add pre_process & post_process layout kernel. test=develop * [Lite][OpenCL]pre_process & post_process layout kernel Code style.test=develop
-
由 xiebaiyuan 提交于
* [LITE][OPENCL][Image] fix issue in concat and nearest_interp thx for chenj and ys,test=develop * [LITE][OPENCL][Image] fix issue in concat and nearest_interp thx for chenj and ys,test=develop
-
- 25 2月, 2020 2 次提交
-
-
由 HappyAngel 提交于
* fix conv 2-pad to 4-pad * fix compute conv shape * fix pad, test=develop * change conv_depthwise_3x3s1_fp.cc name to conv3x3s1p01_depthwise_fp32.cc to distinguish between conv3x3s1_depthwise_fp32.cc * delete printf note in conv3x3s1, test=develop * delete printf note, test=develop * delete gem_sdot.h, test=develop it is coped from __gemm_sdot_meta_.h * update compute padding, test=develop * fix padding size, must be 2 or 4. test=develop * fix format in operators/conv_op.cc, test=develop * change #if 0 to #if 1, test=develop * put 2-pad to 4-pad in AttachImpl, test=develop * fix clang-format error inn tests/math/connv_compute_test, test=develop * fix x86 test result error, test=develop * add asymmetric padding test case in liite/tests/math/conv_compute.cc, test=develop * change paddings type to support dynamically modify, test=develop * fix x86 build error in connv_compute_test, test=develop * fix opencl build error, test=develop * fix oopencl build error, test=develop * fix opencl/conv_compute build error, test=develop * fix opencl/conv_compute build error, test=develop * fix format in kernels/opencl/conv_computte_ttest,test=develop * fix build error, test=develop fix build error in kernels/x86/conv_compute.h * fix ccompute shape error in ooperators/conv_op.h, test=develop * add conv_reelu6 and conv leaky_relu in conv_3x3s1_direct * add conv_relu6 in c1, c2, c4,test=develop * fix conflict in conv_bloock_utils.h, test=develop * add relu6 and leankyrelu in conv_3x3s1_dw * add conv_3x3s1px_dw relu6 and leaky_relu fusion, test=develop * fix conflict in tests/math/conv_compute_arm, test=develop * fix build error in winograd arm, test=develop * channge act_param as pointer in conv_block_tuils.h, test=develop * fix winograd in no equal 4-padding compute error, test=develop * add conv relu6 and leaky_relu in conv_dw_3x3s2, test=develop * fix format, test=develop * fix format in conv_block_utils, test=develop * move updatePadding from conv_op.cc to conv_op.h, test=develop * fix format conv_op.h, test=develop * fix buuilde error in conv_oop.h, test=develop * remove flag_relu parameter in conv_3x3_depthwise, test=develop * add conv relu6/lleakyrelu in sgemm, test=develop * delete some notes, test=develop * fix format, test=develop * fix build moobile_android error, test=develop * change matmul, conv_transpose, mul and fc in using sgemm, test=develop * fix build error in sgemm_test.ccc, test=develop * add act_param in gru_utils. test=develop * fix compute error in conv_dw, test=develop * delete con2d_transpose test, test=develop delete con2d_transpose test, this test can found in test/math/ * fix build error, test=develop * add conv5x5s2_dw. pooling1x1s2_max, conv_act_fusion include relu6 and leaky_relu, teest=develop * fix fc_reluu fusion error, test=develop * fix compute error, test=develop * delete conv5x5s2p2_dw, test=develop * delete extra nnoote, test=develop * delete conv_relu6 fusion in conv_activation_fuse_pass, test=develop * fix build error, test=develop * fix test error in kernel, test=develop kernel/arm/test_pool_compute * fix no equal pooling compute error, test=develop * free space, test=develop * fix con5x5s2_dw compute error, test=develop * fix fromat, test=develop * fix hin compute. test=develop * fix con_dw leakyrelu compute error * fix conv3x3s1_dw leakyRelu compute error * delte note, test=develop * fix format, test=develop * fix format in conv_compute_test, test=develop * add conv+relu6/leakyRelu fusion, test=develop * fix format bug, test=develop * fix format, test=develop * fix format. test=develop * fix format bug, test=develop * fix con+relu6/leakyRelu fusion in Fp32, test=develop * note m=397 in sgemv_int8 ut, test=develop * note m=397 in sgemv_int8 ut, test=develop * fix ios build error. test=develop * add ut * fix calib compute in int32_to_int8, test=develop * add classify ut * add classify demo * add classify demo * fix build error * fix model_test_classify format * fix format, test=develop * fix v7 buiild error * fix run ut errorr * fix format and run ut Error, test=develop * fix build.sh, test=develop * fix format, test=develop * fix format. test=develop * fix format, test=develop * fix no-equal padding , test=develop * fix pooling * add no-equal padding inn pooling, test=develop * fix un-equal padding error. test=develop * fix conv+relu6 int8 fusion error, test=develop * fix int8 conv+relu6 error, test=develop * fix format, test=develop * delete pool_compute_test, test=develop * fix image compute error, test=develop
-
由 xiebaiyuan 提交于
* [LITE][OPENCL][Image] conv 1x1 5x5 7x7 suite # Conflicts: # lite/kernels/opencl/conv_image_compute_test.cc * [LITE][OPENCL][Image] conv 1x1 5x5 7x7 suite,test=develop * [LITE][OPENCL][Image] conv 1x1 5x5 7x7 suite,test=develop * [LITE][OPENCL][Image] conv 1x1 5x5 7x7 suite,test=develop * [LITE][OPENCL][Image] conv 1x1 5x5 7x7 suite,rm1x1 old,test=develop
-
- 24 2月, 2020 3 次提交
-
-
由 cc 提交于
* Support lac model, fix bug for argmax lod_reset, test=develop
-
由 xiebaiyuan 提交于
-
由 Yuan Shuai 提交于
[LITE][OPENCL] support fp16 for cl_image_converter, layout, activation all OpenCL image kernel. test=develop (#2964) * [LITE][OPENCL] support fp16 for cl_image_converter, layout, activation image kernel. test=develop * add conv, depthwise and UT. test=develop * add pool, conv, nearest_interp kernel. test=develop * support fp16 for scale, reshape, concat, fc buffer opencl kernel. test=develop * refactor for mul opencl buffer kernel. test=develop * support fp16 for elementwise_mul opecl image kernel. test=develop * support fp16 for elementwise_mul opencl image kernel. test=develop * support fp16 for ele_add, fuse_ele_add_act opencl kernel. test=develop * rename io_copy. test=develop * mobilenetv1,v2 passed on 855. test=develop * fix opt for opencl. test=develop
-
- 22 2月, 2020 1 次提交
-
-
由 HappyAngel 提交于
-
- 20 2月, 2020 3 次提交
-
-
由 Yuan Shuai 提交于
-
由 Wilber 提交于
Optimize cuda kernel and remove io_copy added by default due to missing fetch_cuda kernel
-
由 HappyAngel 提交于
* fix caliberate error, values from [-128, 127] to [-127, 127], test=develop * add classify demo and detection demo, test=develop
-
- 18 2月, 2020 1 次提交
-
-
由 yiicy 提交于
-
- 14 2月, 2020 3 次提交
-
-
由 Yiqun Liu 提交于
* Optimize softmax. When the input tensor is 2-D and axis is 1, there is no need to resize. * Optimize the gru, avoid calling Tensor::Slice. test=develop * Remove a std::vector in softmax. test=develop * Define CalculateSeqWidth to get the width of a sequence. test=develop
-
由 Yuan Shuai 提交于
* comment All opencl buffer kernels. test=develop * refactor conv, depthwise into one routing selection. test=develop
-
由 xiaogang 提交于
fix fpga lite_tensor compile bug add fake quantize_abs_max op test=develop
-
- 13 2月, 2020 2 次提交
-
-
由 GaoWei8 提交于
* replace gru RowWiseAdd Eigen with c implementation test=develop
-
由 Yuan Shuai 提交于
* [LITE][OPENCL] Add opencl image2d conv3x3. test=develop
-
- 12 2月, 2020 7 次提交
-
-
由 Jiaying Zhao 提交于
* [LITE][OPENCL]Add scale kernel. * [LITE][OPENCL]Add scale kernel, format code style.
-
由 HappyAngel 提交于
add concat ut, test=develop * fix axis compute, test=develop * add other axis, test=develop * fix ut. test=develop
-
由 HappyAngel 提交于
* fix con+relu6/leakyRelu fusion in Fp32, test=develop * note m=397 in sgemv_int8 ut, test=develop * fix ios build error. test=develop
-
由 xiaogang 提交于
fix conv_winograd multithreads bug
-
由 yiicy 提交于
* [ARM] add 5x5s2 depthwise conv armv8 impl, test=develop * [ARM] add int8 5x5s2 dw conv armv7 impl, test=develop * [ARM] add int8 5x5s2 dw conv impl, test=develop * [ARM] close int8 conv ut, test=develop
-
由 yiicy 提交于
[OPENCL] add sigmoid image2d kernel and ut
-
由 xiaogang 提交于
* fix: update fpga backend and kernel test=develop * style: style fix test=develop
-
- 11 2月, 2020 1 次提交
-
-
由 Yiqun Liu 提交于
* Optimize the transform from Paddle' Tensor to EigenVector, avoiding defining multiple DDim. * Optimize the compute implementation of several operators. test=develop
-
- 10 2月, 2020 2 次提交
-
-
由 xiaogang 提交于
-
由 Yuan Shuai 提交于
[LITE][OPENCL] Add 3 kernels of ElementwiseAdd/FusionElemenwiseAddAct op with opencl image format (#2844) * [LITE][OPENCL] Add 3 kernels of ElementwiseAdd/FuseElementwiseAdd op. test=develop
-
- 08 2月, 2020 1 次提交
-
-
由 xiebaiyuan 提交于
* [LITE][OPENCL][Image]develop 1x1/5x5/7x7 routing in conv_compute ,test=develop * [LITE][OPENCL][Image]develop 1x1/5x5/7x7 routing in conv_compute ,convert bias filter in prepare for run ,test=develop
-
- 07 2月, 2020 1 次提交
-
-
由 Yuan Shuai 提交于
* [LITE][OPENCL] remove useless code. test=develop * [LITE][OPENCL] finish 4 kernel and unit tests of image2d opencl elementwise_mul kernel. test=develop * [LITE][OPENCL] Fix little bug of ASSERT. test=develop * [LITE][OPENCL] Fix bug of channel_mul_d2 and d4. test=develop
-
- 05 2月, 2020 1 次提交
-
-
由 HappyAngel 提交于
[arm] fix conv_dw leakyRelu compute error
-
- 04 2月, 2020 1 次提交
-
-
由 yiicy 提交于
* refactor 5x5s1 dw conv armv8, test=develop * [ARM] refactor depthwise conv 5x5s1, and support relu6, leakey relu, test=develop * [ARM] sgemv support fuse relu6 and leakey relu,test=develop * [ARM] reduce some conv ut case, test=develop * [ARM] fix 5x5dw conv pick kernel bug, test=develop * fix code style, test=develop * [ARM] fix sgemv fuse relu6 bug, test=develop * [ARM] fix fp32 5x5s1 dw bug, test=develop * [ARM] fix fp32 5x5 dw conv pick kernel bug, test=develop
-
- 03 2月, 2020 1 次提交
-
-
由 Yuan Shuai 提交于
-