You only look once (YOLO) is a state-of-the-art, real-time object detection system. YOLOv3 is extremely fast and accurate.
- Download the dataset COCO2014.
Prior detection systems repurpose classifiers or localizers to perform detection. They apply the model to an image at multiple locations and scales. High scoring regions of the image are considered detections.
YOLOv3 use a totally different approach. It apply a single neural network to the full image. This network divides the image into regions and predicts bounding boxes and probabilities for each region. These bounding boxes are weighted by the predicted probabilities.
> Unzip the COCO2014 dataset to any path you want, the folder should include train and eval dataset as follows:
YOLOv3 uses a few tricks to improve training and increase performance, including: multi-scale predictions, a better backbone classifier, and more. The full details are in the paper!
In order to reduce the size of the weight and improve the low-bit computing performance, int8 quantization is used.
[Paper](https://pjreddie.com/media/files/papers/YOLOv3.pdf): YOLOv3: An Incremental Improvement. Joseph Redmon, Ali Farhadi,
University of Washington
# [Model Architecture](#contents)
YOLOv3 use DarkNet53 for performing feature extraction, which is a hybrid approach between the network used in YOLOv2, Darknet-19, and that newfangled residual network stuff. DarkNet53 uses successive 3 × 3 and 1 × 1 convolutional layers and has some shortcut connections as well and is significantly larger. It has 53 convolutional layers.
- Note:Data will be processed in yolo_dataset.py, and unzip files before uses it.
# [Environment Requirements](#contents)
- Hardware(Ascend)
- 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.
--lr_gamma LR_GAMMA Decrease lr by a factor of exponential lr_scheduler.
Default: 0.1
--eta_min ETA_MIN Eta_min in cosine_annealing scheduler. Default: 0
--T_max T_MAX T-max in cosine_annealing scheduler. Default: 135
--max_epoch MAX_EPOCH
Max epoch num to train the model. Default: 135
--warmup_epochs WARMUP_EPOCHS
Warmup epochs. Default: 0
--weight_decay WEIGHT_DECAY
Weight decay factor. Default: 0.0005
--momentum MOMENTUM Momentum. Default: 0.9
--loss_scale LOSS_SCALE
Static loss scale. Default: 1024
--label_smooth LABEL_SMOOTH
Whether to use label smooth in CE. Default:0
--label_smooth_factor LABEL_SMOOTH_FACTOR
Smooth strength of original one-hot. Default: 0.1
--log_interval LOG_INTERVAL
Logging interval steps. Default: 100
--ckpt_path CKPT_PATH
Checkpoint save location. Default: "outputs/"
--ckpt_interval CKPT_INTERVAL
Save checkpoint interval. Default: None
--is_save_on_master IS_SAVE_ON_MASTER
Save ckpt on master or all rank, 1 for master, 0 for
all ranks. Default: 1
--is_distributed IS_DISTRIBUTED
Distribute train or not, 1 for yes, 0 for no. Default: 0
--rank RANK Local rank of distributed. Default: 0
--group_size GROUP_SIZE
World size of device. Default: 1
--need_profiler NEED_PROFILER
Whether use profiler. 1 for yes. 0 for no. Default: 0
--training_shape TRAINING_SHAPE
Fix training shape. Default: ""
--resize_rate RESIZE_RATE
Resize rate for multi-scale training. Default: None
```
```
#### Launch
```bash
# distributed training example(8p)
sh run_distribute_train.sh dataset/coco2014 yolov3_darknet_noquant_ckpt/0-320_102400.ckpt rank_table_8p.json
# standalone training example(1p)
## [Training Process](#contents)
sh run_standalone_train.sh dataset/coco2014 yolov3_darknet_noquant_ckpt/0-320_102400.ckpt
```
> About rank_table.json, You can generate it by using the [hccl json configuration file](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/utils/hccl_tools).
### Training on Ascend
#### Result
### Distributed Training
Training result will be stored in the scripts path, whose folder name begins with "train" or "train_parallel". You can find checkpoint file together with result like the followings in log.txt.
```
sh run_distribute_train.sh dataset/coco2014 yolov3_darknet53_noquant.ckpt rank_table_8p.json
```
The above shell script will run distribute training in the background. You can view the results through the file `train_parallel[X]/log.txt`. The loss value will be achieved as follows:
sh run_eval.sh [DATASET_PATH] [CHECKPOINT_PATH] [DEVICE_ID]
```
#### Launch
### Evaluation on Ascend
```bash
Before running the command below.
# infer with checkpoint
sh run_eval.sh dataset/coco2014/ checkpoint/0-131.ckpt 0
```
python eval.py \
--data_dir=./dataset/coco2014 \
--pretrained=0-130_83330.ckpt \
--testing_shape=416 > log.txt 2>&1 &
OR
sh run_eval.sh dataset/coco2014/ checkpoint/0-130_83330.ckpt 0
```
```
> checkpoint can be produced in training process.
The above python command will run in the background. You can view the results through the file "log.txt". The mAP of the test dataset will be as follows:
#### Result
Inference result will be stored in the scripts path, whose folder name is "eval". Under this, you can find result like the followings in log.txt.
```
```
# log.txt
=============coco eval reulst=========
=============coco eval reulst=========
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.310
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.310
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.531
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.531
...
@@ -141,3 +264,51 @@ Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.232
...
@@ -141,3 +264,51 @@ Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.232