@@   Editor:   Horacce
@@   Date  :   2019.03.08

This project is modified from experiencor/keras-yolo3 [origin README.md also provided below], the code is still under polising.

To use this code:

1. modify the config:
   • data load in method: For ['data']['data_load_method']: "origin": origin data read in method, example config: zoo/config_voc.json [voc.py] For ['data']['data_load_method']: "txt": control data load in by a txt file, example config: zoo/config_yolov3-tiny.json [VocFromTxt.py]
   • pretrain model: now cannot support pretrained model, the model will initialize automatically, if anyone can provide, please contact me, thank you.
2. For training: python train.py -c zoo/config_yolov3-tiny.cfg
3. For testing: python predict.py -c zoo/config_yolov3-tiny.cfg -i [image_path] -o [result_dir]

Why use this code:

1. support multi-gpu training [thanks again for experiencor's work]
2. support yolov3-tiny
3. a little bit more stable loss and more convinence than the origin one [maybe = =]

Something updates:

• Type Error Fix in tensor shape setting: now support retangle image train/test
• Yolov3-Tiny support now [For Yolov3, please use the original version]
• allow train without pretrain model
• config modification for convenient usage
• Loss function update [the original version is difficult to converge, new version is better]

ToDo:

• support yolov3
• pretrained model for yolov3-tiny
• different backbones
• easily debug structure for different models in one config

========================================================================================================================================================================

========================================================================================================================================================================

YOLO3 (Detection, Training, and Evaluation)

Dataset and Model

Dataset	mAP	Demo	Config	Model
Kangaroo Detection (1 class) (https://github.com/experiencor/kangaroo)	95%	https://youtu.be/URO3UDHvoLY	check zoo	http://bit.do/ekQFj
Raccoon Detection (1 class) (https://github.com/experiencor/raccoon_dataset)	98%	https://youtu.be/lxLyLIL7OsU	check zoo	http://bit.do/ekQFf
Red Blood Cell Detection (3 classes) (https://github.com/experiencor/BCCD_Dataset)	84%	https://imgur.com/a/uJl2lRI	check zoo	http://bit.do/ekQFc
VOC (20 classes) (http://host.robots.ox.ac.uk/pascal/VOC/voc2012/)	72%	https://youtu.be/0RmOI6hcfBI	check zoo	http://bit.do/ekQE5

Detection

Grab the pretrained weights of yolo3 from https://pjreddie.com/media/files/yolov3.weights.

python yolo3_one_file_to_detect_them_all.py -w yolo3.weights -i dog.jpg

Training

1. Data preparation

Download the Raccoon dataset from from https://github.com/experiencor/raccoon_dataset.

Organize the dataset into 4 folders:

• train_image_folder <= the folder that contains the train images.

• train_annot_folder <= the folder that contains the train annotations in VOC format.

• valid_image_folder <= the folder that contains the validation images.

• valid_annot_folder <= the folder that contains the validation annotations in VOC format.

There is a one-to-one correspondence by file name between images and annotations. If the validation set is empty, the training set will be automatically splitted into the training set and validation set using the ratio of 0.8.

2. Edit the configuration file

The configuration file is a json file, which looks like this:

{
    "model" : {
        "min_input_size":       352,
        "max_input_size":       448,
        "anchors":              [10,13,  16,30,  33,23,  30,61,  62,45,  59,119,  116,90,  156,198,  373,326],
        "labels":               ["raccoon"]
    },

    "train": {
        "train_image_folder":   "/home/andy/data/raccoon_dataset/images/",
        "train_annot_folder":   "/home/andy/data/raccoon_dataset/anns/",      
          
        "train_times":          10,             # the number of time to cycle through the training set, useful for small datasets
        "pretrained_weights":   "",             # specify the path of the pretrained weights, but it's fine to start from scratch
        "batch_size":           16,             # the number of images to read in each batch
        "learning_rate":        1e-4,           # the base learning rate of the default Adam rate scheduler
        "nb_epoch":             50,             # number of epoches
        "warmup_epochs":        3,              # the number of initial epochs during which the sizes of the 5 boxes in each cell is forced to match the sizes of the 5 anchors, this trick seems to improve precision emperically
        "ignore_thresh":        0.5,
        "gpus":                 "0,1",

        "saved_weights_name":   "raccoon.h5",
        "debug":                true            # turn on/off the line that prints current confidence, position, size, class losses and recall
    },

    "valid": {
        "valid_image_folder":   "",
        "valid_annot_folder":   "",

        "valid_times":          1
    }
}

The labels setting lists the labels to be trained on. Only images, which has labels being listed, are fed to the network. The rest images are simply ignored. By this way, a Dog Detector can easily be trained using VOC or COCO dataset by setting labels to ['dog'].

Download pretrained weights for backend at:

https://1drv.ms/u/s!ApLdDEW3ut5fgQXa7GzSlG-mdza6

This weights must be put in the root folder of the repository. They are the pretrained weights for the backend only and will be loaded during model creation. The code does not work without this weights.

3. Generate anchors for your dataset (optional)

python gen_anchors.py -c config.json

Copy the generated anchors printed on the terminal to the anchors setting in config.json.

4. Start the training process

python train.py -c config.json

By the end of this process, the code will write the weights of the best model to file best_weights.h5 (or whatever name specified in the setting "saved_weights_name" in the config.json file). The training process stops when the loss on the validation set is not improved in 3 consecutive epoches.

5. Perform detection using trained weights on image, set of images, video, or webcam

python predict.py -c config.json -i /path/to/image/or/video

It carries out detection on the image and write the image with detected bounding boxes to the same folder.

Evaluation

python evaluate.py -c config.json

Compute the mAP performance of the model defined in saved_weights_name on the validation dataset defined in valid_image_folder and valid_annot_folder.