- 13 9月, 2019 1 次提交
-
-
由 Zhaolong Xing 提交于
-
- 12 9月, 2019 12 次提交
-
-
由 StarryRain 提交于
* add opencl depthwise_conv_trans_op * test=develop * Optimal OPENCL conv_3x3S2 Performance * test=develop * Optimal OPENCL conv_trans_3x3s2 Performance , test=develop * add opencl conv_trans_op, test=develop
-
由 Yan Chunwei 提交于
-
由 zhupengyang 提交于
fix bilinear-interp unit test for more cases test=develop
-
由 lijianshe02 提交于
-
由 huzhiqiang 提交于
add math function: lstm and selected_rows into lite/x86/math add selected_rows and rw_lock into lite/fluid add lstm_cpu_kernel and lstm_kernel into lite/x86/detail
-
由 NazgulLee 提交于
-
由 zp7 提交于
-
由 guofei 提交于
-
由 Wilber 提交于
* add unsqueeze and range op. modify concat op test=develop * modify exception in range_test_x86
-
由 Wilber 提交于
-
由 lijianshe02 提交于
-
由 Wilber 提交于
add transpose kernel for cuda
-
- 11 9月, 2019 5 次提交
-
-
由 Yan Chunwei 提交于
-
由 StarryRain 提交于
* add opencl depthwise_conv_trans_op * test=develop * Optimal OPENCL conv_3x3S2 Performance * test=develop * Optimal OPENCL conv_trans_3x3s2 Performance , test=develop
-
由 石晓伟 提交于
* make passes related to the device type, test=develop * improve tips, test=develop
-
由 liu zhengxi 提交于
add slice op, reshape op, reshape2 op, squeeze op and squeeze2 op and their unittests for x86
-
由 zhupengyang 提交于
test=develop
-
- 10 9月, 2019 7 次提交
-
-
由 lijianshe02 提交于
-
由 Wilber 提交于
-
由 juncaipeng 提交于
* add assign_value op, arm kernel and test, add fluid_type, test=develop * add hard_sigmoid, test=develop * use image and new imple to test detection model, delete faster_rcnn_test, test=develop
-
由 Xiaoyang LI 提交于
fix model_optimize_tool error when using host kernel, fix reshape op build error on ios, test=develop (#1984)
-
由 TianXiaogang 提交于
-
由 NazgulLee 提交于
-
由 StarryRain 提交于
* add opencl depthwise_conv_trans_op * test=develop * Optimal OPENCL conv_3x3S2 Performance * test=develop
-
- 09 9月, 2019 5 次提交
-
-
由 Yanzhan Yang 提交于
* fix vector out of range crash test=develop * fix style test=develop
-
由 NazgulLee 提交于
-
由 juncaipeng 提交于
* add assign_value op, arm kernel and test, add fluid_type, test=develop * add hard_sigmoid, test=develop
-
由 Pei Yang 提交于
* add nearest_interp_cuda kernel, test=develop * add concat op and elementwise_add op * remove eigen dependency from nearest_interp cuda kernel, test=develop * free cuda pointers, test=develop
-
由 Zhen Wang 提交于
* add calib cuda kernel. * add unit test for calib cuda kernel. test=develop
-
- 07 9月, 2019 1 次提交
-
-
由 lijianshe02 提交于
* add lite x86 ops for ASR test=develop * add lite x86 ops for ASR test=develop * fix x86 ci run test problems test=develop * fix mkl path for CI test=develop
-
- 06 9月, 2019 5 次提交
-
-
由 Yanzhan Yang 提交于
* fix ios CPU preprocess test=develop * fix style test=develop
-
由 zhupengyang 提交于
test=develop
-
由 huzhiqiang 提交于
modify reshape2 OP to add shape_tensor input
-
由 Wilber 提交于
* modify slice op and add slice test * modify nearest_polate when align_corners=false (bugfix)
-
由 Zhaolong Xing 提交于
* paddle lite cuda init can run model with leaky_relu * add the missing file. test=develop * add the load from memory interface. test=develop * refine this pr. fix comments fix ci error test=develop * conv impl fp32: conv, conv+bais, conv+bias+relu, conv+bias+leaky_relu int8: conv, conv+bais+relu(int8 or fp32 output), conv+bias+leaky_relu(int8 or fp32 output) can run conv+ bias+relu using cxx_api test=develop * move the lite/cuda/math to backends/cuda/math test=develop
-
- 04 9月, 2019 1 次提交
-
-
由 Wilber 提交于
* modify slice op and add slice test * modify slice op bug
-
- 03 9月, 2019 3 次提交
-
-
由 zp7 提交于
-
由 Yanzhan Yang 提交于
* accelerate opencl compilation time test=develop * fix style test=develop
-
由 tensor-tang 提交于
* fix attr and refine subgraph pass test=develop * refine the npu pass functions * fix test test=develop
-