fix fasterrcnn readme and psenet makefile

This commit is contained in:
linqingke 2020-10-16 15:58:53 +08:00
parent e52588285b
commit a78e22dfdf
2 changed files with 7 additions and 6 deletions

View File

@ -33,7 +33,7 @@ FasterRcnn is a two-stage target detection network,This network uses a region pr
# Dataset
Dataset used: [COCO2017](<http://images.cocodataset.org/>)
Dataset used: [COCO2017](<https://cocodataset.org/>)
- Dataset size19G
- Train18G118000 images
@ -209,7 +209,7 @@ Eval result will be stored in the example path, whose folder name is "eval". Und
| Model Version | V1 |
| Resource | Ascend 910 CPU 2.60GHz192coresMemory755G |
| uploaded Date | 08/31/2020 (month/day/year) |
| MindSpore Version | 0.7.0-beta |
| MindSpore Version | 1.0.0 |
| Dataset | COCO2017 |
| Training Parameters | epoch=12, batch_size=2 |
| Optimizer | SGD |
@ -217,7 +217,7 @@ Eval result will be stored in the example path, whose folder name is "eval". Und
| Speed | 1pc: 190 ms/step; 8pcs: 200 ms/step |
| Total time | 1pc: 37.17 hours; 8pcs: 4.89 hours |
| Parameters (M) | 250 |
| Scripts | https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/faster_rcnn |
| Scripts | [fasterrcnn script](https://gitee.com/mindspore/mindspore/tree/r1.0/model_zoo/official/cv/faster_rcnn) |
### Evaluation Performance
@ -227,7 +227,7 @@ Eval result will be stored in the example path, whose folder name is "eval". Und
| Model Version | V1 |
| Resource | Ascend 910 |
| Uploaded Date | 08/31/2020 (month/day/year) |
| MindSpore Version | 0.7.0-beta |
| MindSpore Version | 1.0.0 |
| Dataset | COCO2017 |
| batch_size | 2 |
| outputs | mAP |
@ -235,4 +235,5 @@ Eval result will be stored in the example path, whose folder name is "eval". Und
| Model for inference | 250M (.ckpt file) |
# [ModelZoo Homepage](#contents)
Please check the official [homepage](https://gitee.com/mindspore/mindspore/tree/master/model_zoo).
Please check the official [homepage](https://gitee.com/mindspore/mindspore/tree/master/model_zoo).

View File

@ -14,7 +14,7 @@
# ============================================================================
mindspore_home = ${MINDSPORE_HOME}
CXXFLAGS = -I include -I ${mindspore_home}/mindspore/official/cv/psenet -std=c++11 -O3
CXXFLAGS = -I include -I ${mindspore_home}/model_zoo/official/cv/psenet -std=c++11 -O3
CXX_SOURCES = adaptor.cpp
opencv_home = ${OPENCV_HOME}
OPENCV = -I$(opencv_home)/include -L$(opencv_home)/lib64 -lopencv_superres -lopencv_ml -lopencv_objdetect \