- 10 8月, 2020 2 次提交
-
-
由 driftcloudy 提交于
* [Ascend] add fc op * [Ascend] fix fc test * [Ascend] fix code format * [Ascend] modify the comment
-
由 HappyAngel 提交于
* fix sequence pool grad compute error, test=develop * fix sequence pool grad run, test=develop * fix format test=develop
-
- 07 8月, 2020 4 次提交
-
-
由 hong19860320 提交于
[Core] Fix the missing of the input and output scale after the lite_elementwise_activation_fuse_pass is applied (#4066)
-
由 Qi Li 提交于
-
由 石晓伟 提交于
-
由 Qi Li 提交于
* [ascend] add softmax and dropout op, test=develop * [Ascend] address review comments, test=develop
-
- 06 8月, 2020 6 次提交
-
-
由 Qinghe JING 提交于
* add support for three-dimentional input in reduce max test=develop
-
由 Wilber 提交于
-
由 石晓伟 提交于
* add view suffix to read-only classes for flatbuffers, test=develop * add some write-apis for flatbuffers, test=develop
-
由 Qi Li 提交于
* [ascend] add pool and elementwise op, test=develop * [ascend] add batch_norm op and simpify tensor update, test=develop
-
由 zhupengyang 提交于
-
由 hong19860320 提交于
test=develop
-
- 05 8月, 2020 4 次提交
-
-
由 huzhiqiang 提交于
-
由 myq406450149 提交于
* change pooling3x3s2max padding right to intrisic. test=develop
-
由 ysh329 提交于
* add int32->int64 cast arm cpu kernel. test=develop
-
由 石晓伟 提交于
* [test] flatbuffers io, test=develop * determine the basic interfaces and help functions of flatbuffers, test=develop
-
- 04 8月, 2020 7 次提交
-
-
由 Leonardo-Ding 提交于
-
由 hong19860320 提交于
[RKNPU] Adapting to the changing of the quantization parameters, and supporting the fully quantized mobilenetv1 model (#4046) * [RKNPU] Adapting to the changing of the quantization parameters, and supporting the fully quantized mobilenetv1 model test=develop * [Doc] Update the doc for apu and rknpu test=develop
-
由 cc 提交于
-
由 石晓伟 提交于
* add ParamDesc, test=develop * serialize tensor funcs, test=develop
-
由 huzhiqiang 提交于
-
由 Wilber 提交于
-
由 Qi Li 提交于
-
- 03 8月, 2020 2 次提交
-
-
由 Qi Li 提交于
-
由 huzhiqiang 提交于
-
- 30 7月, 2020 6 次提交
-
-
由 Qi Li 提交于
-
由 HappyAngel 提交于
* update prior profile, test=develop * fix review. test=develop * test=develop
-
由 石晓伟 提交于
-
由 ysh329 提交于
* fix opencl backend. test=develop
-
由 ysh329 提交于
-
由 hong19860320 提交于
[ARM] [NPU] Fix the overflow of layer_norm op bridge, fix the registration of lstm op kernel (#4007) (#4017) * [NPU] Fix the overflow of layer_norm op bridge test=develop * [ARM] Fix the registration of lstm op kernel test=develop
-
- 29 7月, 2020 4 次提交
-
-
由 石晓伟 提交于
-
由 HappyAngel 提交于
* fix arm winograd compute segment. test=develop
-
由 huzhiqiang 提交于
[Framework] Fix the issue that `CreatePaddlePredictor` method is not safe for multi-thread condition #4014
-
由 myq406450149 提交于
-
- 28 7月, 2020 1 次提交
-
-
由 蔡舒起 提交于
-
- 27 7月, 2020 4 次提交
-
-
由 蔡舒起 提交于
-
由 HappyAngel 提交于
* add elu act * fix elu act not find error, test=develop * fix format.test=develop * fix int8 model opt error in conv+conv fusion, test=develop * fix format. test=develop * test=develop
-
由 myq406450149 提交于
* add op affine_grid. test=develop * fix format. test=develop * change arm transpose kernel. develop=test
-
由 Santa An 提交于
* [LITE][BM] modify interpolate if,test=develop * [LITE][BM] compiler opt=1 to opt=2, test=develop
-