未验证 提交 0e567a06 编写于 作者: W Wei Shengyu 提交者: GitHub

Update PULC_model_list.md

上级 c04c8786
......@@ -12,7 +12,7 @@
| safety_helmet |[PULC佩戴安全帽分类模型](PULC_safety_helmet.md)| 99.38 |6.5M|2.03ms|[推理模型](https://paddleclas.bj.bcebos.com/models/PULC/inference/safety_helmet_infer.tar) / [预训练模型](https://paddleclas.bj.bcebos.com/models/PULC/pretrained/safety_helmet_pretrained.pdparams)|
| traffic_sign |[PULC交通标志分类模型](PULC_traffic_sign.md)| 98.35 |8.2M|2.10ms|[推理模型](https://paddleclas.bj.bcebos.com/models/PULC/inference/traffic_sign_infer.tar) / [预训练模型](https://paddleclas.bj.bcebos.com/models/PULC/pretrained/traffic_sign_pretrained.pdparams)|
| vehicle_attribute |[PULC车辆属性识别模型](PULC_vehicle_attribute.md)| 90.81 |7.2M|2.36ms|[推理模型](https://paddleclas.bj.bcebos.com/models/PULC/inference/vehicle_attribute_infer.tar) / [预训练模型](https://paddleclas.bj.bcebos.com/models/PULC/pretrained/vehicle_attribute_pretrained.pdparams)|
| vehicle_exists |PULC有车/无车分类模型 | 95.72 | 6.6M | 2.38ms |[推理模型](https://paddleclas.bj.bcebos.com/models/PULC/inference/vehicle_exists_infer.tar) / [预训练模型](https://paddleclas.bj.bcebos.com/models/PULC/pretrained/vehicle_exists_pretrained.pdparams)|
| vehicle_exists |PULC有车/无车分类模型 | 95.92 | 6.6M | 2.38ms |[推理模型](https://paddleclas.bj.bcebos.com/models/PULC/inference/vehicle_exists_infer.tar) / [预训练模型](https://paddleclas.bj.bcebos.com/models/PULC/pretrained/vehicle_exists_pretrained.pdparams)|
| text_image_orientation |[PULC含文字图像方向分类模型](PULC_text_image_orientation.md)| 99.06 | 6.5M | 2.16ms |[推理模型](https://paddleclas.bj.bcebos.com/models/PULC/inference/text_image_orientation_infer.tar) / [预训练模型](https://paddleclas.bj.bcebos.com/models/PULC/pretrained/text_image_orientation_pretrained.pdparams)|
| textline_orientation |[PULC文本行方向分类模型](PULC_textline_orientation.md)| 96.01 |6.5M|2.72ms|[推理模型](https://paddleclas.bj.bcebos.com/models/PULC/inference/textline_orientation_infer.tar) / [预训练模型](https://paddleclas.bj.bcebos.com/models/PULC/pretrained/textline_orientation_pretrained.pdparams)|
| language_classification |[PULC语种分类模型](PULC_language_classification.md)| 99.26 |6.5M|2.58ms|[推理模型](https://paddleclas.bj.bcebos.com/models/PULC/inference/language_classification_infer.tar) / [预训练模型](https://paddleclas.bj.bcebos.com/models/PULC/pretrained/language_classification_pretrained.pdparams)|
......@@ -22,4 +22,4 @@
* 以上所有的模型的 backbone 均为 PPLCNet_x1_0,部分模型大小不同是由于分类的输出大小不同导致的,推理耗时是基于Intel(R) Xeon(R) Gold 6148 CPU @ 2.40GHz 测试得到,其中测试过程开启 MKLDNN 加速策略,线程数为10。速度测试过程会有轻微波动。
* person_exists、safety_helmet、vehicle_exists 的评测指标为 TprAtFpr,person_attribute、vehicle_attribute的评测指标为ma、traffic_sign、text_image_orientation、textline_orientation、language_classification的评测指标为Top-1 Acc。
\ No newline at end of file
* person_exists、safety_helmet、vehicle_exists 的评测指标为 TprAtFpr,person_attribute、vehicle_attribute的评测指标为ma、traffic_sign、text_image_orientation、textline_orientation、language_classification的评测指标为Top-1 Acc。
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册