Before FasterRcnn, the target detection networks rely on the region proposal algorithm to assume the location of targets, such as SPPnet and Fast R-CNN. Progress has reduced the running time of these detection networks, but it also reveals that the calculation of the region proposal is a bottleneck.
FasterRcnn proposed that convolution feature maps based on region detectors (such as Fast R-CNN) can also be used to generate region proposals. At the top of these convolution features, a Region Proposal Network (RPN) is constructed by adding some additional convolution layers (which share the convolution characteristics of the entire image with the detection network, thus making it possible to make regions almost costlessProposal), outputting both region bounds and objectness score for each location.Therefore, RPN is a full convolutional network (FCN), which can be trained end-to-end, generate high-quality region proposals, and then fed into Fast R-CNN for detection.
@ -35,14 +35,14 @@ FasterRcnn is a two-stage target detection network,This network uses a region pr
Note that you can run the scripts based on the dataset mentioned in original paper or widely used in relevant domain/network architecture. In the following sections, we will introduce how to run the scripts using the related dataset below.
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 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`.
# Quick Start
After installing MindSpore via the official website, you can start training and evaluation as follows:
After installing MindSpore via the official website, you can start training and evaluation as follows:
Note: 1.the first run will generate the mindeocrd file, which will take a long time.
2.pretrained model is a resnet50 checkpoint that trained over ImageNet2012.
3.VALIDATION_JSON_FILE is label file. CHECKPOINT_PATH is a checkpoint file after trained.
3.VALIDATION_JSON_FILE is label file. CHECKPOINT_PATH is a checkpoint file after trained.
```
```shell
# standalone training
sh run_standalone_train_ascend.sh [PRETRAINED_MODEL]
@ -110,7 +110,7 @@ sh run_eval_ascend.sh [VALIDATION_JSON_FILE] [CHECKPOINT_PATH]
```shell
.
└─faster_rcnn
└─faster_rcnn
├─README.md // descriptions about fasterrcnn
├─scripts
├─run_standalone_train_ascend.sh // shell script for standalone on ascend
@ -139,27 +139,26 @@ sh run_eval_ascend.sh [VALIDATION_JSON_FILE] [CHECKPOINT_PATH]
```
## Training Process
### Usage
```
```shell
# standalone training on ascend
sh run_standalone_train_ascend.sh [PRETRAINED_MODEL]
# distributed training on ascend
sh run_distribute_train_ascend.sh [RANK_TABLE_FILE] [PRETRAINED_MODEL]
```
> Rank_table.json which is specified by RANK_TABLE_FILE is needed when you are running a distribute task. You can generate it by using the [hccl_tools](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/utils/hccl_tools).
> As for PRETRAINED_MODEL，it should be a ResNet50 checkpoint that trained over ImageNet2012. Ready-made pretrained_models are not available now. Stay tuned.
> The original dataset path needs to be in the config.py,you can select "coco_root" or "image_dir".
### 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.
The [mixed precision](https://www.mindspore.cn/tutorial/training/en/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 formats, 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’.
## [Environment Requirements]
## Environment Requirements
- Hardware（Ascend）
- Prepare hardware environment with Ascend. If you want to try Ascend, please send the [application form](https://obs-9be7.obs.cn-east-2.myhuaweicloud.com/file/other/Ascend%20Model%20Zoo%E4%BD%93%E9%AA%8C%E8%B5%84%E6%BA%90%E7%94%B3%E8%AF%B7%E8%A1%A8.docx) to ascend@huawei.com. Once approved, you can get the resources.
@ -69,9 +69,9 @@ For FP16 operators, if the input data type is FP32, the backend of MindSpore wil
[论文](https://openaccess.thecvf.com/content_CVPR_2019/html/Wang_Shape_Robust_Text_Detection_With_Progressive_Scale_Expansion_Network_CVPR_2019_paper.html)： Wenhai Wang, Enze Xie, Xiang Li, Wenbo Hou, Tong Lu, Gang Yu, Shuai Shao; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 9336-9345
mindspore-ci-bot
4 years ago
committed by
Gitee