Each row is an image annotation which split by space, the first column is a relative path of image, the others are box and class infomations of the format [xmin,ymin,xmax,ymax,class]. We read image from an image path joined by the `IMAGE_DIR`(dataset directory) and the relative path in `ANNO_PATH`(the TXT file path), `IMAGE_DIR` and `ANNO_PATH` are setting in `config.py`.
Each row is an image annotation which split by space, the first column is a relative path of image, the others are box and class information of the format [xmin,ymin,xmax,ymax,class]. We read image from an image path joined by the `IMAGE_DIR`(dataset directory) and the relative path in `ANNO_PATH`(the TXT file path), `IMAGE_DIR` and `ANNO_PATH` are setting in `config.py`.
# Quick Start
@ -242,7 +242,7 @@ Notes:
### Result
Training result will be stored in the example path, whose folder name begins with "train" or "train_parallel". You can find checkpoint file together with result like the followings in loss_rankid.log.
Training result will be stored in the example path, whose folder name begins with "train" or "train_parallel". You can find checkpoint file together with result like the following in loss_rankid.log.
```log
# distribute training result(8p)
@ -265,10 +265,12 @@ sh run_eval_ascend.sh [VALIDATION_JSON_FILE] [CHECKPOINT_PATH]
```
> checkpoint can be produced in training process.
>
> Images size in dataset should be equal to the annotation size in VALIDATION_JSON_FILE, otherwise the evaluation result cannot be displayed properly.
### Result
Eval result will be stored in the example path, whose folder name is "eval". Under this, you can find result like the followings in log.
Eval result will be stored in the example path, whose folder name is "eval". Under this, you can find result like the following in log.
```log
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.360
Training result will be stored in the example path, whose folder name begins with "train" or "train_parallel". You can find checkpoint file together with result like the followings in loss_rankid.log.
Training result will be stored in the example path, whose folder name begins with "train" or "train_parallel". You can find checkpoint file together with result like the following in loss_rankid.log.
> As for the COCO2017 dataset, VALIDATION_ANN_FILE_JSON is refer to the annotations/instances_val2017.json in the dataset directory.
> checkpoint can be produced and saved in training process, whose folder name begins with "train/checkpoint" or "train_parallel*/checkpoint".
>
> Images size in dataset should be equal to the annotation size in VALIDATION_ANN_FILE_JSON, otherwise the evaluation result cannot be displayed properly.
### [Evaluation result](#content)
Inference result will be stored in the example path, whose folder name is "eval". Under this, you can find result like the followings in log.
Inference result will be stored in the example path, whose folder name is "eval". Under this, you can find result like the following in log.
"roi_sample_num": 640, # sample number in ROIAling layer
@ -338,7 +338,7 @@ sh run_distribute_train.sh [RANK_TABLE_FILE] [PRETRAINED_MODEL]
### [Training Result](#content)
Training result will be stored in the example path, whose folder name begins with "train" or "train_parallel". You can find checkpoint file together with result like the followings in loss_rankid.log.
Training result will be stored in the example path, whose folder name begins with "train" or "train_parallel". You can find checkpoint file together with result like the following in loss_rankid.log.
```bash
# distribute training result(8p)
@ -369,7 +369,7 @@ sh run_eval.sh [VALIDATION_ANN_FILE_JSON] [CHECKPOINT_PATH]
### [Evaluation result](#content)
Inference result will be stored in the example path, whose folder name is "eval". Under this, you can find result like the followings in log.
Inference result will be stored in the example path, whose folder name is "eval". Under this, you can find result like the following in log.
gengdongjie
4 years ago