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.
[Paper](https://arxiv.org/abs/1506.01497): Ren S , He K , Girshick R , et al. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 39(6).
FasterRcnn is a two-stage target detection network,This network uses a region proposal network (RPN), which can share the convolution features of the whole image with the detection network, so that the calculation of region proposal is almost cost free. The whole network further combines RPN and FastRcnn into a network by sharing the convolution features.
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.
- Prepare hardware environment with Ascend processor. 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.
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`.
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.you can train it with [resnet50](https://gitee.com/qujianwei/mindspore/tree/master/model_zoo/official/cv/resnet) scripts in modelzoo, and use src/convert_checkpoint.py to get the pretrain model.
3. BACKBONE_MODEL is a checkpoint file trained with [resnet50](https://gitee.com/qujianwei/mindspore/tree/master/model_zoo/official/cv/resnet) scripts in modelzoo.PRETRAINED_MODEL is a checkpoint file after convert.VALIDATION_JSON_FILE is label file. CHECKPOINT_PATH is a checkpoint file after trained.
1. 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).
2. As for PRETRAINED_MODEL，it should be a trained ResNet50 checkpoint. If you need to load Ready-made pretrained FasterRcnn checkpoint, you may make changes to the train.py script as follows.
```python
# Comment out the following code
# load_path = args_opt.pre_trained
# if load_path != "":
# param_dict = load_checkpoint(load_path)
# for item in list(param_dict.keys()):
# if not item.startswith('backbone'):
# param_dict.pop(item)
# load_param_into_net(net, param_dict)
# Add the following codes after optimizer definition since the FasterRcnn checkpoint includes optimizer parameters：
lr = Tensor(dynamic_lr(config, rank_size=device_num), mstype.float32)
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.
