detectron2：使用API函数训练自己的coco格式的数据集

0. load 基本的依赖库

# You may need to restart your runtime prior to this, to let your installation take effect
# Some basic setup
# Setup detectron2 logger
import detectron2
from detectron2.utils.logger import setup_logger
setup_logger()

# import some common libraries
import matplotlib.pyplot as plt
import numpy as np
import cv2
from google.colab.patches import cv2_imshow

# import some common detectron2 utilities
from detectron2.engine import DefaultPredictor
from detectron2.config import get_cfg
from detectron2.utils.visualizer import Visualizer
from detectron2.data import MetadataCatalog, DatasetCatalog

1. 注册自己coco格式的数据集：
按照 Detectron2 自定义数据集教程，将自己的数据集注册到 Detectron2。

from detectron2.data.datasets import register_coco_instances

register_coco_instances('self_coco_train', {}, 
                        '/home/workspace/datasets/cocodatasets_2017/annotations/instances_train2017.json', 
                       '/home/workspace/datasets/cocodatasets_2017/train2017')
register_coco_instances('self_coco_val', {}, 
                        '/home/workspace/datasets/cocodatasets_2017/annotations/instances_val2017.json', 
                       '/home/workspace/datasets/cocodatasets_2017/val2017')

获取数据的元数据

coco_val_metadata = MetadataCatalog.get("self_coco_val")
dataset_dicts = DatasetCatalog.get("self_coco_val")
coco_val_metadata

原始数据可视化

import random

for d in random.sample(dataset_dicts, 3):
    img = cv2.imread(d["file_name"])
    visualizer = Visualizer(img[:, :, ::-1], metadata=coco_val_metadata, scale=0.5)
    vis = visualizer.draw_dataset_dict(d)
    cv2_imshow(vis.get_image()[:, :, ::-1])

2.模型训练
加载基本的配置

from detectron2.engine import DefaultTrainer
from detectron2.config import get_cfg
from detectron2 import model_zoo

cfg = get_cfg()
cfg.merge_from_file(model_zoo.get_config_file("COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml"))
cfg.DATASETS.TRAIN = ("self_coco_train",)
cfg.DATASETS.TEST = ("self_coco_val", )
cfg.DATALOADER.NUM_WORKERS = 2
cfg.MODEL.WEIGHTS = model_zoo.get_checkpoint_url("COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml")  # Let training initialize from model zoo
cfg.SOLVER.IMS_PER_BATCH = 2
cfg.SOLVER.BASE_LR = 0.00025  # pick a good LR
cfg.SOLVER.MAX_ITER = 300    # 300 iterations seems good enough for this toy dataset; you may need to train longer for a practical dataset
cfg.MODEL.ROI_HEADS.BATCH_SIZE_PER_IMAGE = 128   # faster, and good enough for this toy dataset (default: 512)
cfg.MODEL.ROI_HEADS.NUM_CLASSES = 80  # coco datasets

cfg

训练与保存模型

import os 

os.makedirs(cfg.OUTPUT_DIR, exist_ok=True)

trainer = DefaultTrainer(cfg)
trainer.resume_or_load(resume=False)
trainer.train()

3.预测
加载已经训练好的模型

cfg.MODEL.WEIGHTS = os.path.join(cfg.OUTPUT_DIR, "model_final.pth")
cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.5   # set the testing threshold for this model
cfg.DATASETS.TEST = ("self_coco_val", )
predictor = DefaultPredictor(cfg)

预测结果可视化

from detectron2.utils.visualizer import ColorMode

for d in random.sample(dataset_dicts, 3):    
    im = cv2.imread(d["file_name"])
    outputs = predictor(im)
    v = Visualizer(im[:, :, ::-1],
                   metadata=coco_val_metadata, 
                   scale=0.8, 
                   instance_mode=ColorMode.IMAGE_BW   # remove the colors of unsegmented pixels
    )
    v = v.draw_instance_predictions(outputs["instances"].to("cpu"))
    cv2_imshow(v.get_image()[:, :, ::-1])