- 07 5月, 2019 1 次提交
-
-
由 Jiaying Zhao 提交于
* optimize GPU conv performance and structure * add CL macro for test_conv_gpu * fix build failure * change funtion name * change funtion name
-
- 06 5月, 2019 2 次提交
-
-
由 Yanzhan Yang 提交于
* implement winograd for metal depthwise 3x3 naively * keep half4 in non-winograd depthwise 3x3 to ensure precision
-
由 Jiaying Zhao 提交于
* optimize GPU conv performance and structure * add CL macro for test_conv_gpu * fix build failure
-
- 30 4月, 2019 4 次提交
-
-
由 Yanzhan Yang 提交于
-
由 NazgulLee 提交于
-
由 qnqinan 提交于
* update concat and split kernel and related files in FPGA v2(v3) track * update * update * update kernel and related files in FPGA v2 track * update * update * update kernel and related files for static quantization in FPGA v2 track * update
-
由 Shuai Yuan 提交于
* format CMakeLists * BugFix: lacking of header file of memset, strlen, stable_sort, n_copy * Update ARM Linux CPU, GPU build docs for rk3399
-
- 29 4月, 2019 3 次提交
-
-
由 Yanzhan Yang 提交于
* fuse Conv-Add-Relu into one op. * Revert "fuse Conv-Add-Relu into one op." This reverts commit 200be579. * fuse Conv-Add-Relu into one op
-
由 WayneLiu 提交于
-
由 qnqinan 提交于
* update concat and split kernel and related files in FPGA v2(v3) track * update * update * update kernel and related files in FPGA v2 track * update * update
-
- 28 4月, 2019 1 次提交
-
-
由 Houjiang Chen 提交于
* Fix memory leak if tensor was created outside of global scope * Fix gemv bugs
-
- 26 4月, 2019 3 次提交
-
-
由 Yanzhan Yang 提交于
fix MPSCNN ConvAdd implementation.
-
由 yangyanzhan 提交于
-
由 Jiaying Zhao 提交于
adjust gpu code structure
-
- 25 4月, 2019 8 次提交
-
-
由 zhaojiaying01 提交于
-
由 zhaojiaying01 提交于
-
由 zhaojiaying01 提交于
-
由 Jiaying Zhao 提交于
-
由 zhaojiaying01 提交于
-
由 Jiaying Zhao 提交于
fix gpu conv_kernel
-
由 zhaojiaying01 提交于
-
由 zhaojiaying01 提交于
-
- 24 4月, 2019 1 次提交
-
-
由 Shuai Yuan 提交于
* BugFix: add input parameters checking for Alloc * Give advice for Alloc function users * Give advice for Alloc function users
-
- 23 4月, 2019 3 次提交
-
-
由 tensor-tang 提交于
-
由 Houjiang Chen 提交于
-
由 Shuai Yuan 提交于
* BugFix: fix multi-threadings incorrectness of cpu gemm * BugFix: fix lack of header file for memset * BugFix: fix lacking of header file for memset
-
- 22 4月, 2019 4 次提交
-
-
由 jameswu2014 提交于
update some files related with static quantization in FPGA V2 track fixed#1570
-
由 qnqinan 提交于
-
-
由 Chon 提交于
* FPGA refactor * disable FPGAKD * recover misdeleted code segment
-
- 19 4月, 2019 4 次提交
-
-
由 qnqinan 提交于
-
由 qnqinan 提交于
-
由 jameswu2014 提交于
add static quantization code and update FPGA V2(V3) related files fixed #1563
-
由 qnqinan 提交于
-
- 17 4月, 2019 2 次提交
-
-
由 xiebaiyuan 提交于adapter new xcode & remove annotation
-
由 xiebaiyuan 提交于
-
- 15 4月, 2019 1 次提交
-
-
由 Houjiang Chen 提交于
* Clear no persistable tensor array before predicting, fix crash when predicting with gpu debugging mode * Fix code style * Add fetch API for java, refine android log
-
- 12 4月, 2019 2 次提交
-
-
由 Shuai Yuan 提交于
* add prepare data and model script, modified corresponding docs:development_android and development_android_GPU * Add verified multi-threading supported gemv_trans_mx1 * add comments for alloc and free * optimize reduction progress of gemv_trans_mx1 * add macro for gemv_trans_mx1 * Fix multi-threadings incorrectnesss of armv7 neon gemv_trans_mx1 * add test_gemm_accuracy
-
由 WayneLiu 提交于
-
- 04 4月, 2019 1 次提交
-
-
由 Houjiang Chen 提交于
Clear no persistable tensor array before predicting, fix crash when predicting with gpu debugging mode (#1548) * Clear no persistable tensor array before predicting, fix crash when predicting with gpu debugging mode * Fix code style
-