LL-XSJ

_base_ = [ '../_base_/datasets/coco_detection.py', '../_base_/default_runtime.py' ] # model settings num_dec_layer = 6 lambda_2 = 2.0 # 在修改配置文件训练自己的数据集的时候，一共有3个地方需要修改类别数量 model = dict( type='CoDETR', backbone=dict( type='ResNet', depth=50, num_stages=4, out_indices=(1, 2, 3), frozen_stages=1, norm_cfg=dict(type='BN',...

Hello author, is this the training config? I'm worried that I gave it the wrong way

Yes, I have modified the category and number of training rounds of the dataset. Will this affect the training of multiple nodes?