Comments (3)
Could you confirm if the detection results you passed to generate_attack_targets
contain at least one object?
from tog.
For both the images and some other images also, it is showing the same error. The detection_query
is returning an empty array which is being passed into the generate_attack_targets
So, I think this may be the reason for the above error, is that so? If it is because of this, can you please resolve it as it won't run for all test images (4972) in PASCAL VOC 2007 dataset then?
from tog.
The above error is generated by empty detection results on benign images. Having at least one detected object is needed for mislabeling attacks as the goal of the attack is to fool the detector to mislabel an existing object. Since the images to be skipped depend on the detector you use, it is recommended to simply add an if-clause to skip if the number of detected objects is zero.
from tog.
Related Issues (20)
- module 'cupy.cuda.memory' has no attribute 'PythonFunctionAllocatorMemory' for FRCNN HOT 4
- TypeError: Keras symbolic inputs/outputs do not implement `__len__` HOT 4
- yolov5 HOT 1
- Video Example HOT 1
- 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_360' (op: 'Assign') with input shapes: [1,1,1024,75], [255,1024,1,1]. HOT 7
- running the projects on colab HOT 2
- No Object Detection Metrics Computation HOT 1
- vanishing attack and fabrication Attack HOT 1
- patch HOT 1
- visualize results HOT 1
- get mAP HOT 1
- TOG patch and position HOT 1
- Dont have from model.bbox_transform and net.vgg HOT 1
- too many wrong outcomes HOT 4
- 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 HOT 1
- ZeroDivisionError: division by zero
- don't have .h5 file HOT 1
- Getting Shape related Issue while loading the weight file in yolov3.
- 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]. HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from tog.