How to evaluate the base training performance?

[Jesse2hong]

Hi there! thanks for sharing the great work! But I have a problem in evaluating the base training performance. I downloaded the pre_trained weights that you released, and conducted inference without any fine-tuning. Follows are my inference command and the results on base classes. I don't know why the performance is far worse than that you released. Could you please give me some clue?

python -u main.py \ --dataset_file coco_base \ --backbone resnet101 \ --num_feature_levels 1 \ --enc_layers 6 \ --dec_layers 6 \ --hidden_dim 256 \ --num_queries 300 \ --batch_size 2 \ --category_codes_cls_loss \ --resume path/to/checkpoint.pth \ --fewshot_finetune \ --fewshot_seed 1 \ --num_shots 10 \ --eval \ 2>&1 | tee ./log_inference.txt

• Base Categories: Accumulating evaluation results... DONE (t=12.80s). IoU metric: bbox Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.079 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.108 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.087 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.043 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.096 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.118 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.271 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.421 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.421 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.184 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.476 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.677