fast-reid/fastreid/utils
liaoxingyu 13bb03eb07 feat: add rank result visualization tools
Update visualization tools which can save rank list with AP metrics from high to low, vice versa.
In order to compute AP fast in visualizer, modify rank_cylib to get all_AP instead of mAP.
In this way, we can use Cython to compute results.
2020-05-10 23:17:10 +08:00
..
__init__.py Update sampler code 2020-02-10 07:38:56 +08:00
checkpoint.py feat(layers/norm): add ghost batchnorm 2020-05-01 09:02:46 +08:00
comm.py Update sampler code 2020-02-10 07:38:56 +08:00
events.py Finish first version for fastreid 2020-02-10 22:13:04 +08:00
file_io.py Update sampler code 2020-02-10 07:38:56 +08:00
history_buffer.py Update sampler code 2020-02-10 07:38:56 +08:00
logger.py Update sampler code 2020-02-10 07:38:56 +08:00
one_hot.py feat(layers/norm): add ghost batchnorm 2020-05-01 09:02:46 +08:00
precision_bn.py feat(layers/norm): add ghost batchnorm 2020-05-01 09:02:46 +08:00
registry.py Update sampler code 2020-02-10 07:38:56 +08:00
rerank.py Update sampler code 2020-02-10 07:38:56 +08:00
summary.py Update sampler code 2020-02-10 07:38:56 +08:00
timer.py Update sampler code 2020-02-10 07:38:56 +08:00
visualizer.py feat: add rank result visualization tools 2020-05-10 23:17:10 +08:00
weight_init.py feat(layers/norm): add ghost batchnorm 2020-05-01 09:02:46 +08:00