Xiao Tianci
5 years ago
3 changed files with 3 additions and 3 deletions
Unified View
Diff Options
-
+1 -1model_zoo/official/cv/ssd/README.md
-
+1 -1model_zoo/official/cv/yolov3_resnet18/README.md
-
+1 -1model_zoo/research/cv/ssd_ghostnet/README.md
+ 1
- 1
model_zoo/official/cv/ssd/README.md
View File
| @@ -147,7 +147,7 @@ sh run_eval.sh [DATASET] [CHECKPOINT_PATH] [DEVICE_ID] | |||||
| ### Training on Ascend | ### Training on Ascend | ||||
| To train the model, run `train.py`. If the `mindrecord_dir` is empty, it will generate [mindrecord](https://www.mindspore.cn/tutorial/training/zh-CN/master/advanced_use/converse_dataset.html) files by `coco_root`(coco dataset) or `iamge_dir` and `anno_path`(own dataset). **Note if mindrecord_dir isn't empty, it will use mindrecord_dir instead of raw images.** | |||||
| To train the model, run `train.py`. If the `mindrecord_dir` is empty, it will generate [mindrecord](https://www.mindspore.cn/tutorial/training/zh-CN/master/advanced_use/convert_dataset.html) files by `coco_root`(coco dataset) or `iamge_dir` and `anno_path`(own dataset). **Note if mindrecord_dir isn't empty, it will use mindrecord_dir instead of raw images.** | |||||
| - Distribute mode | - Distribute mode | ||||
+ 1
- 1
model_zoo/official/cv/yolov3_resnet18/README.md
View File
| @@ -135,7 +135,7 @@ After installing MindSpore via the official website, you can start training and | |||||
| ## [Training Process](#contents) | ## [Training Process](#contents) | ||||
| ### Training on Ascend | ### Training on Ascend | ||||
| To train the model, run `train.py` with the dataset `image_dir`, `anno_path` and `mindrecord_dir`. If the `mindrecord_dir` is empty, it wil generate [mindrecord](https://www.mindspore.cn/tutorial/training/zh-CN/master/advanced_use/converse_dataset.html) file by `image_dir` and `anno_path`(the absolute image path is joined by the `image_dir` and the relative path in `anno_path`). **Note if `mindrecord_dir` isn't empty, it will use `mindrecord_dir` rather than `image_dir` and `anno_path`.** | |||||
| To train the model, run `train.py` with the dataset `image_dir`, `anno_path` and `mindrecord_dir`. If the `mindrecord_dir` is empty, it wil generate [mindrecord](https://www.mindspore.cn/tutorial/training/zh-CN/master/advanced_use/convert_dataset.html) file by `image_dir` and `anno_path`(the absolute image path is joined by the `image_dir` and the relative path in `anno_path`). **Note if `mindrecord_dir` isn't empty, it will use `mindrecord_dir` rather than `image_dir` and `anno_path`.** | |||||
| - Stand alone mode | - Stand alone mode | ||||
+ 1
- 1
model_zoo/research/cv/ssd_ghostnet/README.md
View File
| @@ -134,7 +134,7 @@ python eval.py --device_id 0 --dataset coco --checkpoint_path LOG4/ssd-500_458.c | |||||
| ### Training on Ascend | ### Training on Ascend | ||||
| To train the model, run `train.py`. If the `mindrecord_dir` is empty, it will generate [mindrecord](https://www.mindspore.cn/tutorial/training/zh-CN/master/advanced_use/converse_dataset.html) files by `coco_root`(coco dataset) or `iamge_dir` and `anno_path`(own dataset). **Note if mindrecord_dir isn't empty, it will use mindrecord_dir instead of raw images.** | |||||
| To train the model, run `train.py`. If the `mindrecord_dir` is empty, it will generate [mindrecord](https://www.mindspore.cn/tutorial/training/zh-CN/master/advanced_use/convert_dataset.html) files by `coco_root`(coco dataset) or `iamge_dir` and `anno_path`(own dataset). **Note if mindrecord_dir isn't empty, it will use mindrecord_dir instead of raw images.** | |||||
| - Distribute mode | - Distribute mode | ||||