Comments (5)
Similarly please share ImageNet model used as initialization!
No such file or directory: '/scratch2/model_weights/ssd300_12_imagenet.pth'
from visda-2018-public.
My bad. I believe it must be this one, and you convert it to proper format using this script. And I believe that the best file to start with would be this one
from visda-2018-public.
Same problem after following your instruction.
I suppose it could be caused by pytorch version mismatch. I run this script under pytorch=0.4 and I noticed your pytorch version is older(you are using Variable()
API).
I suggest you provide us a requirements.txt or environment.yaml(for conda) to make thins clear.
from visda-2018-public.
That probably means that, for some reason, one of tensors turn contained nan
or value outsize of propeor range, I guess? If you could share somehow what are vales of these tensors, which of them are suspicious and suggest how did they manage to get these values, I might try to guess why it might have happened. This code worked fine for me, I usually do not push broken code intentionally :)
from visda-2018-public.
When I turned into torchcv, most of the problems disappeared.
But the so called device-side assert triggered
is caused by misconfiguration(the number of class of a model should be #foreground_classes + 1
, which included the background as one class).
from visda-2018-public.
Related Issues (20)
- request for README of pytorch-ssd-mmd-coral HOT 8
- where is the knife class? HOT 1
- what is the difference between score and mean accuracy? HOT 3
- Detection competition - unable to submit predictions to CodaLab HOT 4
- Detection ground truths don't match the coco17 validation ground truths HOT 4
- [open set domain adaptation] Use test image when training HOT 3
- Error: source file does not contain the same number of elements as truth file. HOT 3
- Where to find the test data for detection track
- Detection track test set contains no image_list.txt HOT 4
- Invalid images in detection track test set HOT 1
- Inconsistent dates on CodaLab & Task CV homepage HOT 3
- My submission's status is submitted for a lone time HOT 1
- #Detection Track# Submission failed due to out-of-service platform HOT 3
- Something wrong with the result board HOT 3
- Have not noticed the deadline of submitting the form. HOT 6
- can we submit abstract now? HOT 2
- How to download CAD models? HOT 2
- synthetic
- Is there any license offered for the dataset? HOT 1
- How to recognize textured images from plain albedo synthetic images
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 visda-2018-public.