- 13 3月, 2018 1 次提交
-
-
由 chengduoZH 提交于
-
- 12 3月, 2018 1 次提交
-
-
由 chengduoZH 提交于
-
- 07 3月, 2018 2 次提交
-
-
由 pzelazko-intel 提交于
* MKLDNN conv2 OP kernel added * TODOs added * mkldnn conv2d OP refactor * CanCUDNNBeUsed and CanMKLDNNBeUsed moved
-
由 Yan Chunwei 提交于
-
- 06 3月, 2018 4 次提交
-
-
由 qingqing01 提交于
* Fix mAP evaluator bug. * Fix bug in detection mAP evaluator. * Fix unit testing. * Support to set background label index in detection mAP op.
-
由 qiaolongfei 提交于
-
由 Qiao Longfei 提交于
* change learning_rate_decay to learning_rate_scheduler * optimize code * change nn.cast to tensor.cast
-
由 qingqing01 提交于
Implement detection mAP evaluator wrapper and unify label format between SSD loss and mAP evaluator (#8736) * Implement mAP evalutor Python interface. * Fix unit testing and uniy label format between SSD loss and mAP evalutor. * Update doc.
-
- 05 3月, 2018 2 次提交
- 01 3月, 2018 1 次提交
-
-
由 Xin Pan 提交于
-
- 28 2月, 2018 4 次提交
-
-
由 Yuan Gao 提交于
* fix ssd problems * fix box decoder op * fix dimension problem in detection tests * update detection doc * Update detection doc * Update detection doc * update detection doc * update detection doc
-
由 Yu Yang 提交于
-
由 wanghaoshuang 提交于
-
由 xuwei06 提交于
When the second argument contains batch dimension, the axis should be 0. Also makes elementwise ops more tolerant at handling tensors with trailing singular dimensions.
-
- 27 2月, 2018 4 次提交
-
-
由 chengduoZH 提交于
-
由 Yu Yang 提交于
-
由 Xin Pan 提交于
-
由 qingqing01 提交于
* Enhance bipartite_match_op to support argmax matching after bipartite matching. * Fix typo error.
-
- 26 2月, 2018 3 次提交
- 24 2月, 2018 2 次提交