RobustDet
RobustDet copied to clipboard
7eu7d7
The official PyTorch implementation of "Adversarially-Aware Robust Object Detector"
Dear author: Congratulations on having your paper published in 2022 ECCV Oral! Also , thanks your great project! I have encountered a problem while evaluation result in VOC dataset with...
Reproduced on the VOC dataset using the scripts and parameters used in readme, with only two parameters modified (batch size reduced and lr reduced). The local trained model and the...
Hi! When I train the model with train_robust.py, I met this problem: When I run the command to train with VOC dataset on cuda device, it shows `TypeError: can't convert...
As you've mentioned in readme.md, both CWAT and MTD have no official code for training or evaluation. I've tried to reproduce CWAT and MTD by the train_adv.py with exactly the...
I see that when training VOC, the parameters are set as follows lr_steps: (80000, 100000, 120000), but set max_iteration=40000 in the training cfg file, what is the specific relevant setting....
Hello author, could you please take a look at why the loss has always been nan when training mtd, and not nan when training cwat, but the loss has always...
There's some problems when I training on VOC. As you instructed, I use command `CUDA_VISIBLE_DEVICES=1,2,3 python train_robust.py --cfg cfgs/RobustDet_voc.yaml --adv_type mtd --data_use clean --multi_gpu True --basenet weights/ssd300_mAP_77.43_v2.pth --dataset_root dataset/VOCdevkit` for...
hello, could you please add the code to visualize the attack and defense of robust_ssd?
The code can be run properly with a single GPU. But when I applied the option multi-gpus=True, the DataParallel used in the code went wrong. To be specific, the hook...
