TOG

TOG copied to clipboard

Thank you very much for your work, it's very beneficial, can you give the code that implements the real-time video attack?

zhongyubunenghunl

Shape Related Issue while loading the model. ValueError: Dimension 0 in both shapes must be equal, but are 1 and 255. Shapes are [1,1,1024,75] and [255,1024,1,1]. for 'Assign_1082' (op: 'Assign') with input shapes: [1,1,1024,75], [255,1024,1,1].

1

Hi, I used the pretrained model, which is working fine. but when I am training keras-yolov3 model with following steps: 1-> converted the VOC annotations to specific format mentioned in...

praddhumnasoni

don't have .h5 file

1

Dear authors: I'm running the demo on yolov3,but I don't have YOLOv3_Darknet53.h5 file.Can you supply the file？ Thanks a lot！

TanYuzhen

Note: Going through the yolov3_darknet demo file in colab. The error while trying to load the model file. Note: .h5 file is downloaded from the given link in notebook only....

praddhumnasoni

ZeroDivisionError Traceback (most recent call last) in 69 # Compute training statistics 70 epoch_loss = float(np.mean(epoch_loss)) ---> 71 ASR_TOG = score_adv / num_rois 72 ASR_Rand = score_rand / num_rois 73...

s5377689

How do I solve the IndexError: list index out of range error when using tensorflow-gpu==2.5.0 for execute the demo_patch.ipynb program

1

from attack_utils.patch_utils import extract_roi, evaluate_vanishing_patch, evaluate_mislabeling_patch from dataset_utils.preprocessing import letterbox_image_padded from models.yolov3 import YOLOv3_Darknet53 from misc_utils.visualization import visualize_detections from tensorflow.keras import backend as K from tqdm import tqdm from PIL...

s5377689

get mAP

1

I have trained the yolov3 model with my own dataset. I want to get the mAP before and after the attack. I saw in your paper that you also recorded...

wmrenr

too many wrong outcomes

4

I don't know how to solve it.I create the virtual environment as the requirements.txt.when I run,the picture is full of wrong boxes.

xc3217

TOG patch and position

1

Have you ever tried to generate a single channel patch? Does the placement of the patch affect the experimental results?

wmrenr

Dont have from model.bbox_transform and net.vgg

1

For demo_frcnn.ipynb， in FRCNN.py : from model.bbox_transform import clip_boxes, bbox_transform_inv from nets.vgg16 import vgg16 from model.config import cfg Can't find

shiyuf1004