Comments (14)
Ok my username is tgorm and I'd love some free credits. I've tried uploading using zpy upload sim but i get the following error: No such command 'sim'. Would love a fix for this please.
from zpy.
We have a CLI that allows you to upload a local blender simulation and generate images in the cloud. More info on the CLI in our docs. You can also view and download these datasets on our webapp. A quick caveat though: we just pushed a bunch of changes to the CLI & WebApp today, so it might be buggy (we love feedback).
from zpy.
The way we see it the local device is just intended to be used for debugging. We provide the ability to generate images at scale from a sim using our configured backend using our WebApp (https://app.zumolabs.ai) and cli (https://zumolabs.github.io/zpy/cli/about/).
Through the addon you should be able to export the sim and then using the cli you should be able to upload the sim and generate datasets from the sim.
zpy sim upload <sim_name> path/to/exported/sim.zip
zpy dataset generate <dataset_name> <sim_name> <num_frames>
then you should be able to view the dataset on
https://app.zumolabs.ai/datasets
Let me know when you create an account and we can enable 5k in free generation credits for you.
from zpy.
You can export a local simulation by hitting the Export Sim
button on the zpy addon panel:
from zpy.
This new cli format went live earlier today. I would make sure your zpy-zumo
python package is at version 1.3.0
from zpy.
Yep, I just did a new pip install of zpy-zumo, so I'm unsure if that is the issue. Is this what you mean or do you mean the package in. Blender?
from zpy.
Yes you will also need to update the zpy-zumo
the addon is using as we export more information from scenes from before.
The error on the command zpy sim upload
no such command sim is probably due to our new CLI swapping from zpy upload sim
to zpy sim upload
from zpy.
Ok I will do that. Also another question regarding your generation times. If I want a full HD 1080p image and roughly 75% of the image needs to be segmented into categories, how long would something like that take per sim step in your experience? It's taking close to 10mins per step for me currently
from zpy.
After uploading the sim you can see the amount of time in seconds it will take to generate one step under time
. Hard to tell without running it and seeing how the objects are loading and such.
https://app.zumolabs.ai/sims/fb6d9af9-3b17-4c9c-b9bd-784f08ccd24c/metadata
from zpy.
Ok sounds good. And if I run out of generation credits how much do they cost moving forward?
from zpy.
Still something we are figuring out ourselves. Would love feedback to what would feel good from a user perspective.
Our current implementation is some cost per time spent running on the machines which is correlated to our own spending costs.
https://aws.amazon.com/ec2/instance-types/p2/
from zpy.
Hey, I'll need to try itout before giving feedback I think.
Im currently getting this error when trying to run the sim: raise JSONDecodeError("Expecting value", s, err.value) from None
json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0). Could you help me resolve this please
from zpy.
The sim failed to ingress so you will be unable to generate images from it until the sim ingress is successful.
I believe this error is related to the sim being exported with the old version of the addon 1.2.3
as you can see above.
from zpy.
Just added backwards compatibility for old scenes so you should be able to upload the current sim you have and have it ingress successfully if you want to give it another shot.
from zpy.
Related Issues (20)
- Help message for `zpy dataset generate` is improperly formatted
- Package Sim Notebook
- Cannot create COCO annotations when RGB and Segmentation images are in Separate folder HOT 4
- Segmentation taking more and more time as my script is running HOT 2
- typo in zpy/render.py HOT 1
- Attribute Error on zpy.objects.segment HOT 2
- Convert COCO annotations .json file to TensorFlow .record file HOT 2
- Bounding Box generation Error HOT 7
- Can't get denoised render from zpy generated dataset HOT 2
- Attributerror: "rendersettings" object has no attribute "tile_x" (blender 3.0) HOT 1
- Single bounding box for multiple instances HOT 2
- AttributeError: 'Object' object has no attribute 'seg' HOT 1
- ZPY Add-on can not be activated on Blender
- An error with 'tile_x' HOT 2
- Headless Execution Instructions HOT 2
- How to get the Normalised segmentation?
- Did not update the self.category_name_to_id in remap function.
- HDRI & texture randomisation HOT 1
- Material jitter
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 zpy.