def fasterrcnn_resnet50_fpn() example test

training phase

import torch
import torchvision
from torchvision.models.detection import FasterRCNN_ResNet50_FPN_Weights

model = torchvision.models.detection.fasterrcnn_resnet50_fpn(weights=FasterRCNN_ResNet50_FPN_Weights.DEFAULT)

# for train
# 以前一直有误区以为rand会生成4，或者3，这不是乱套了嘛，应该按顺序生成呀，实际上这是维数。浅显理解就是逐渐堆叠,先生成1200列，