- 23 1月, 2019 2 次提交
-
-
由 qingqing01 提交于
* Add generate_mask_labels_op to support Mask-RCNN. * Refine sigmoid_cross_entropy to support nomalize mode. * Fix generator_proposals_label. * Use DeviceTemporaryAllocator in roi_pool and roi_algin. * Remove shape check in data_feeder.
-
由 Yiqun Liu 提交于
* Add check of input in sequence_expand op. test=develop * Correct the unittest of sequence_expand op. test=develop
-
- 22 1月, 2019 1 次提交
-
-
由 WangZhen 提交于
-
- 21 1月, 2019 1 次提交
-
-
由 Dun 提交于
* mem opt * test=develop * test=develop * test=develop * test=develop * test=develop * test=develop * test=develop * refine code test=develop * refine code test=develop * refine code test=develop * refine code test=develop * refine with cub test=develop * fix mkldnn test && remove comments && test=develop * polish code && test=develop * add only_forward test && test=develop
-
- 18 1月, 2019 2 次提交
-
-
由 zhaozhehao 提交于
* refactor tree2col operator with new memory mechanism test=develop * test=develop * test=develop * Modified API according to panyx0718 test=develop * fix API change according to heavengate test=develop * Modify API comment test=develop
-
由 chengduo 提交于
test=develop
-
- 16 1月, 2019 4 次提交
- 15 1月, 2019 5 次提交
-
-
由 peizhilin 提交于
test=develop
-
由 Xin Pan 提交于
test=develop
-
由 Xin Pan 提交于
-
由 mozga-intel 提交于
test=develop
-
由 Qiao Longfei 提交于
-
- 14 1月, 2019 5 次提交
-
-
由 Xin Pan 提交于
test=develop
-
由 Xin Pan 提交于
test=develop
-
由 chengduo 提交于
* open fetch_feed_op test test=develop * code refine test=develop * reset timeout for test_parallel_executor_fetch_feed test=develop * disable test_parallel_executor_fetch_feed for windows test=develop * refine unit test test=develop
-
由 Xin Pan 提交于
test=develop
-
由 tensor-tang 提交于
test=develop
-
- 13 1月, 2019 2 次提交
-
-
由 tensor-tang 提交于
test=develop
-
由 tensor-tang 提交于
test=develop
-
- 11 1月, 2019 2 次提交
- 10 1月, 2019 4 次提交
-
-
由 xiaolil1 提交于
* Enable basic MKL-DNN INT8 Conv OP test=develop * Modify test case test=develop * Clean unittest code test=develop * Fix test test=develop * Modify test test=develop * Enable MKL-DNN INT8 Conv with Relu Fusion OP test=develop * Enable INT8 Conv with residual fusion OP test=develop * Modify code. test=develop * Modify basic INT8 Conv test=develop * Modify Conv. test=develop * fix style test=develop * Fix style test=develop * Fix test test=develop * Modify code. test=develop * Fix test test=develop
-
由 chengduo 提交于
test=develop
-
由 Wu Yi 提交于
* clip softmax for fp16 * updates * fuse xent support fp16 test=develop * wip * wip * add simple row reduce * wip fp16 accurate softmax * add accurate softmax kernel for fp16 test=develop * update test=develop * fix cpu build test=develop * update api.spec test=develop * follow comments test=develop * fix build test=develop * fix trt build test=develop * fix inference build test=develop * fix merge test=develop * update test=develop * try fix build test=develop * fix build test=develop * rename real_exp test=develop * fortest * remove hacky kernels test=develop * clean up test=develop
-
由 flame 提交于
-
- 09 1月, 2019 6 次提交
-
-
由 minqiyang 提交于
-
由 minqiyang 提交于
-
由 Qiao Longfei 提交于
-
由 Qiao Longfei 提交于
test=develop
-
由 Xin Pan 提交于
test=develop
-
由 Xin Pan 提交于
test=develop
-
- 08 1月, 2019 4 次提交
-
-
由 mozga-intel 提交于
test=develop
-
由 peizhilin 提交于
-
由 Xin Pan 提交于
test=develop
-
由 Xin Pan 提交于
test=develop
-
- 07 1月, 2019 2 次提交
-
-
由 tensor-tang 提交于
-
由 xiaolil1 提交于
* Enable basic MKL-DNN INT8 Conv OP test=develop * Modify test case test=develop * Clean unittest code test=develop * Fix test test=develop * Modify test test=develop * Enable MKL-DNN INT8 Conv with Relu Fusion OP test=develop * Modify basic INT8 Conv test=develop * fix type test=develop * Modify test test=develop
-