- 17 3月, 2020 4 次提交
-
-
由 Wilber 提交于
- 增加cuda c++ demo. - 考虑到检测模型尾部一般是multiclass_nms,该kernel为host,如果fetch kernel为cuda的话,则会在此处插入无用的io_copy(host->cuda),由于该原因,注释掉fetch的cuda kernel. 默认使用host的fetch kernel. 此处暗中进行的行为:每次predictor run完,都会默认把数据从cuda拷贝到cpu
-
由 Santa An 提交于
* * support download bm_sdk, test=develop * [LITE][BM] add slice op * [LITE][BM] fix concat issue * [LITE][BM] support reduce full ops, test=develop * [LITE][BM] change test_resnet50 to change test_classify * [LITE][BM] add cast op * [LITE][BM] add reduce and other ops, test=develop * [LITE][BM] add reduce,cast and other ops, test=develop
-
由 Wilber 提交于
add cuda ci. Organize cuda compilation products.
-
由 mapingshuo 提交于
* add sgd op, test=develop * test=develop
-
- 16 3月, 2020 4 次提交
-
-
由 hong19860320 提交于
-
由 mapingshuo 提交于
* add backend * add kernel * add grad kernel
-
由 cc 提交于
-
由 zhupengyang 提交于
* [NPU] subgraph's precision register to kAny
-
- 15 3月, 2020 2 次提交
-
-
由 Yuan Shuai 提交于
* [LITE][OPENCL] Change fp32 fc to fp16's. test=develop * fix act in conv3x3opt opencl kernel. test=develop * [LITE][OPENCL] fix opencl fc kernel. test=develop * [LITE][OPENCL] add lws for opencl conv image kernel. test=develop
-
由 xiebaiyuan 提交于
-
- 14 3月, 2020 2 次提交
-
-
由 Yuan Shuai 提交于
* [LITE][OPENCL] Change fp32 fc to fp16's. test=develop * fix act in conv3x3opt opencl kernel. test=develop * [LITE][DEMO] fix input arg. test=develop * fix shutdownlog for std::endl. test=develop
-
由 Yuan Shuai 提交于
* [LITE][OPENCL] Change fp32 fc to fp16's. test=develop * fix act in conv3x3opt opencl kernel. test=develop
-
- 13 3月, 2020 3 次提交
-
-
由 Jiaying Zhao 提交于
-
由 xiaogang 提交于
-
由 HappyAngel 提交于
* fix clang v7 error * change ut, test=develop * fix conv ut, test=develop
-
- 12 3月, 2020 2 次提交
-
-
由 hong19860320 提交于
* [Core] Fix findar for Clang test=develop * [CORE] Fix the missing of feed and fetch kernel when using light API to loade the optimized model test=develop
-
由 mapingshuo 提交于
* add mean op, test=develop * split forward and backward, test=develop
-
- 11 3月, 2020 1 次提交
-
-
由 yiicy 提交于
add pad2d image kernel and ut
-
- 10 3月, 2020 5 次提交
-
-
由 hong19860320 提交于
-
由 xiaogang 提交于
* feat: add dropout opencl kernel
-
由 HappyAngel 提交于
* fix v7 clang bug. test=develop * fix format, test=develop * fix .a build bug, test=develop
-
由 zhupengyang 提交于
* [NPU] revert shape check for input&output * [NPU] reshape elt input&output
-
由 xiaogang 提交于
* feat: add opencl elementwise_sub op & ut
-
- 09 3月, 2020 9 次提交
-
-
由 yiicy 提交于
add instance norm kernel and ut
-
由 HappyAngel 提交于
* set arm_lang default is off. test=develop * fix resize error, test-develop
-
由 mapingshuo 提交于
* add lookup_dequant_op
-
由 zhupengyang 提交于
-
由 mapingshuo 提交于
-
由 xiaogang 提交于
* feat: add opencl elementwise_sub op & ut
-
由 zhupengyang 提交于
* enhance gather, lookup_table arm kernel uts * enhance beam_search, beam_search_decoder, increment rigster
-
由 Santa An 提交于
-
由 xiebaiyuan 提交于
[LITE][OPENCL][Image] revert router of depthwisespl --> fix mnasnet and nanoyolo ,test=develop (#3109)
-
- 08 3月, 2020 1 次提交
-
-
由 HappyAngel 提交于
* add lrn op * fix v7 build error, test=develop
-
- 07 3月, 2020 3 次提交
-
-
由 xiebaiyuan 提交于
-
由 Jiaying Zhao 提交于
* [Lite][OpenCL]fix depthwise_conv3*3 test. test=develop * [Lite][OpenCL]fix depthwise_conv3*3 test, format codestyle. test=develop
-
由 zhupengyang 提交于
* get the precision from the real tensor or tensor_array of base_scope in arena/framwork * register assign and assign_value to kAny
-
- 06 3月, 2020 3 次提交
-
-
由 HappyAngel 提交于
* fix * fix format. test=develop * fix format, test=develop * fix resize error * fix format. test=develop * fix format, test=develop * fix format * note log(4) << x_image. test=develop * note x_image printf. test=develop
-
由 zhangshijin 提交于
* [MLU] support resnet50 on MLU * [MLU] support resnet50 on MLU
-
由 xiaogang 提交于
* fix: fix nlp ops input and output type * fix: add elementwise x_dims>y_dims case
-
- 05 3月, 2020 1 次提交
-
-
由 zhupengyang 提交于
-