- 06 3月, 2018 1 次提交
-
-
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 3 次提交
-
-
由 fengjiayi 提交于
-
由 qingqing01 提交于
* Refine the doc in detection_output API. * Refine the doc.
-
由 fengjiayi 提交于
-
- 02 3月, 2018 1 次提交
-
-
由 fengjiayi 提交于
-
- 28 2月, 2018 6 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 qiaolongfei 提交于
-
由 qingqing01 提交于
-
由 qiaolongfei 提交于
-
由 qingqing01 提交于
* Register more data type for reshape operator. * Enable the SSD loss to support normalization by the total number of output locations. * Fix the doc format.
-
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 2 次提交
-
-
由 Yu Yang 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 5 次提交
-
-
由 wanghaox 提交于
-
由 chengduoZH 提交于
-
由 Yu Yang 提交于
-
由 Yu Yang 提交于
-
由 chengduoZH 提交于
-
- 24 2月, 2018 1 次提交
-
-
由 Luo Tao 提交于
-