adynathos / road-anomaly-benchmark Goto Github PK
View Code? Open in Web Editor NEWBenchmark of detection methods for anomalies and obstacles in traffic images.
Benchmark of detection methods for anomalies and obstacles in traffic images.
I just meet the a question.
Here we can see there are 100 images in the Anomaly track test. And I download it with 100 correct image. But when i try to inference with
ev = Evaluation(
method_name = 'S2M',
# dataset_name = 'ObstacleTrack-all',
dataset_name = 'AnomalyTrack-test',
)
It said I show prepare 110 images.
File "/detectron2/road-anomaly-benchmark/road_anomaly_benchmark/datasets/tracks.py", line 41, in check_size
raise ValueError(f'The dataset should have {desired_len} frames but found {actual_len}')
ValueError: The dataset should have 110 frames but found 100
How could I solve it? Thank you!
Hi,
I got this error: NoneType' object has no attribute 'bin_edges' during visiualization,
and i dont know what cause this error.Could you give me some infomation about the possible reasons about this error>
thanks a lot!
Hi, I'm trying to evaluate my models on the SMIYC benchmark, I downloaded the RoadObstacle and RoadAnomaly datasets. Each of these contains a total of 442 and 110 images.
I'm confused since the RoadObstacle is supposed to have a total of 327+30 images according to the dataset overview, instead of 442.
One of the LostAndFound dataset links is dead, (this link) and the other provided link, which supposedly has a total of 2104 annotated images, has a validation subset of 1204 images plus 1044 training images.
Are these the correct counts of images?
Hi, this is a great work.
But it seems that the road mask for the obstacle track is not available, which is necessary for us to evaluate our method.
Moreover, the exmaple inference code road-anomaly-benchmark/example_inference.py can not run with certain label file. I'm not sure whether it is the road mask.
Errors are as follows:
[Errno 2] No such file or directory: '/mnt/lustre/yangfan4/road-anomaly-benchmark-master/datasets/dataset_ObstacleTrack/labels_masks/curvy-street_inliner_hubcap_5_labels_semantic.png'
Sorry for interrupting you on International Labour Day, but I found some problems in reusing your repo.
These two following datasets have no public downloading source( or possibly I can't find it), would you please tell me how to download them?
Fishyscapes LostAndFound - Anomalies
LostAndFound - Obstacles
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.