Comments (5)
Can you please provide me with a sample test fall image so I can reproduce the error and fix it?
from fall-detection.
No, because the error is intermittent and since it is not handled in a way that provides much context, I cannot correlate the message to an image. Please think how we can better encapsulate this error with a contextual information in the log that allows us to track it down.
from fall-detection.
ok...will check it.
from fall-detection.
I have tried to trace this issue but unable to locate the bug.
This function use output data(heatmap_data, offset_data) that are generated from TFLite posenet model.
pose_kps[i, 0] = int(remap_pos[0] + offset_data[max_val_pos[0], max_val_pos[1], i])
pose_kps[i, 0] = int(remap_pos[0] + offset_data[max_val_pos[0], max_val_pos[1], i]) TypeError: only size-1 arrays can be converted to Python scalars
And this error is raised when the function expects a single value but you pass an array instead.
I am trying to check at what circumstance model output is different. But not able to find it.
Can you please help me with your thoughts to deal with this bug?
thanks
from fall-detection.
It's not obvious to me what the issue is. Is it possible that
remap_pos[0]
returns anything but a scalar?
Same question for offset_data[max_val_pos[0], max_val_pos[1], i]
.
One of these two returns a list or array, which confuses int().
I suggest surrounding these lines with an exception handling block that provides as much context as needed. That way the next time this happens, we would know exactly what caused it.
from fall-detection.
Related Issues (20)
- move fall detection library out of ambianic-edge into independent pypi package HOT 2
- feat: reduce false positives when there are multiple persons in view
- Image pre-processing for improved PoseNet inference results
- User labeling and model training of fall detection model
- False positive - people bending over intentionally, not falling HOT 3
- Align our PoseDetector API with the TFJS version from Google
- Publish pose-detection as a standalone repo and pypi package
- Switch to MoveNet as a default ML model
- Jupyter Notebook on Fall Detection data
- Clean up python package naming
- [BUG] Fall detection saves debugging images at INFO level HOT 1
- Edge not detecting people walking in and out and not detecting falls, false positives for objects and falls
- Fall detection does not report all the falls
- Implement more test cases based on public and user contributed video and image data of elderly falls HOT 3
- Upgrade pose detection from PoseNet MobileNetV1 to MoveNet, PoseNet 2.0 ResNet50, or BlazePose HOT 10
- Enhance store.py (save_detections) for fall detection
- Optimize CPU usage - rotate image only if there is a standing up pose in the frame buffer HOT 2
- [BUG] fall detection: spinal vector unused for leaning angle calculations HOT 1
- [BUG] Fall detection test fails intermittently in PR #282 HOT 16
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 fall-detection.