For more details please check out our [Architecture Guide](https://www.mindspore.cn/doc/note/en/master/design/mindspore/architecture.html) (visit [Architecture Guide](https://www.mindspore.cn/docs/en/master/architecture.html) before Sep. 24).
For more details please check out our [Architecture Guide](https://www.mindspore.cn/doc/note/en/master/design/mindspore/architecture.html).
### Automatic Differentiation
### Automatic Differentiation
@ -208,7 +208,7 @@ please check out [docker](docker/README.md) repo for the details.
## Quickstart
## Quickstart
See the [Quick Start](https://www.mindspore.cn/tutorial/training/en/master/quick_start/quick_start.html) (visit [Quick Start](https://www.mindspore.cn/tutorial/en/master/quick_start/quick_start.html) before Sep. 24)
See the [Quick Start](https://www.mindspore.cn/tutorial/training/en/master/quick_start/quick_start.html)
The [mixed precision](https://www.mindspore.cn/tutorial/zh-CN/master/advanced_use/mixed_precision.html) training method accelerates the deep learning neural network training process by using both the single-precision and half-precision data types, and maintains the network precision achieved by the single-precision training at the same time. Mixed precision training can accelerate the computation process, reduce memory usage, and enable a larger model or batch size to be trained on specific hardware.
The [mixed precision](https://www.mindspore.cn/tutorial/training/zh-CN/master/advanced_use/enable_mixed_precision.html) training method accelerates the deep learning neural network training process by using both the single-precision and half-precision data types, and maintains the network precision achieved by the single-precision training at the same time. Mixed precision training can accelerate the computation process, reduce memory usage, and enable a larger model or batch size to be trained on specific hardware.
For FP16 operators, if the input data type is FP32, the backend of MindSpore will automatically handle it with reduced precision. Users could check the reduced-precision operators by enabling INFO log and then searching ‘reduce precision’.
For FP16 operators, if the input data type is FP32, the backend of MindSpore will automatically handle it with reduced precision. Users could check the reduced-precision operators by enabling INFO log and then searching ‘reduce precision’.
# [Environment Requirements](#contents)
# [Environment Requirements](#contents)
@ -70,8 +70,8 @@ For FP16 operators, if the input data type is FP32, the backend of MindSpore wil
@ -176,7 +176,7 @@ Note the results is two-classification(person and face) used our own annotations
## [Evaluation Process](#contents)
## [Evaluation Process](#contents)
### Evaluation on Ascend
### Evaluation on Ascend
To eval, run `eval.py` with the dataset `image_dir`, `anno_path`(eval txt), `mindrecord_dir` and `ckpt_path`. `ckpt_path` is the path of [checkpoint](https://www.mindspore.cn/tutorial/training/en/master/use/save_and_load_model.html) file.
To eval, run `eval.py` with the dataset `image_dir`, `anno_path`(eval txt), `mindrecord_dir` and `ckpt_path`. `ckpt_path` is the path of [checkpoint](https://www.mindspore.cn/tutorial/training/en/master/use/save_model.html) file.
```
```
sh run_eval.sh 0 yolo.ckpt ./Mindrecord_eval ./dataset ./dataset/eval.txt
sh run_eval.sh 0 yolo.ckpt ./Mindrecord_eval ./dataset ./dataset/eval.txt
zhangyi
4 years ago