Comments (13)
I suggest ignoring the UX part for now and just dump the crops the same way the boxed images are saved. Users can then look at the crop dir in the file system and copy relevant faces to the known faces directory.
Very useful and only a few lines of code needed π
Mvh.
Torkil
from mlapi.
This would be useful, but one would need to figure out how to make this happen easily from a "UX" perspective. mlapi/ES are both backend servers with no UI per se, so when an unknown face is detected, how do we "ask" the user who this is?
from mlapi.
please give it a whirl
See config.ini for unknown_face related changes
from mlapi.
Great!
Pulled and enabled. For some reason persons are detected almost always but face detections are few and far between so it might take a bit before I can give any feedback.
from mlapi.
192.168.40.138 - - [01/Feb/2020 08:34:48] "POST /api/v1/detect/object?type=face&delete=True HTTP/1.1" 500 - Error on request: Traceback (most recent call last): File "/usr/local/lib64/python3.6/site-packages/werkzeug/serving.py", line 304, in run_wsgi execute(self.server.app) File "/usr/local/lib64/python3.6/site-packages/werkzeug/serving.py", line 292, in execute application_iter = app(environ, start_response) File "/usr/local/lib/python3.6/site-packages/flask/app.py", line 2463, in __call__ return self.wsgi_app(environ, start_response) File "/usr/local/lib/python3.6/site-packages/flask/app.py", line 2449, in wsgi_app response = self.handle_exception(e) File "/usr/local/lib/python3.6/site-packages/flask_restful/__init__.py", line 269, in error_router return original_handler(e) File "/usr/local/lib/python3.6/site-packages/flask/app.py", line 1866, in handle_exception reraise(exc_type, exc_value, tb) File "/usr/local/lib/python3.6/site-packages/flask/_compat.py", line 38, in reraise raise value.with_traceback(tb) File "/usr/local/lib/python3.6/site-packages/flask/app.py", line 2446, in wsgi_app response = self.full_dispatch_request() File "/usr/local/lib/python3.6/site-packages/flask/app.py", line 1951, in full_dispatch_request rv = self.handle_user_exception(e) File "/usr/local/lib/python3.6/site-packages/flask_restful/__init__.py", line 269, in error_router return original_handler(e) File "/usr/local/lib/python3.6/site-packages/flask/app.py", line 1820, in handle_user_exception reraise(exc_type, exc_value, tb) File "/usr/local/lib/python3.6/site-packages/flask/_compat.py", line 38, in reraise raise value.with_traceback(tb) File "/usr/local/lib/python3.6/site-packages/flask/app.py", line 1949, in full_dispatch_request rv = self.dispatch_request() File "/usr/local/lib/python3.6/site-packages/flask/app.py", line 1935, in dispatch_request return self.view_functions[rule.endpoint](**req.view_args) File "/usr/local/lib/python3.6/site-packages/flask_restful/__init__.py", line 458, in wrapper resp = resource(*args, **kwargs) File "/usr/local/lib/python3.6/site-packages/flask/views.py", line 89, in view return self.dispatch_request(*args, **kwargs) File "/usr/local/lib/python3.6/site-packages/flask_restful/__init__.py", line 573, in dispatch_request resp = meth(*args, **kwargs) File "/usr/local/lib/python3.6/site-packages/flask_jwt_extended/view_decorators.py", line 108, in wrapper return fn(*args, **kwargs) File "/root/mlapi/api.py", line 125, in post detections = m.detect(image) File "/root/mlapi/modules/face_recognition.py", line 77, in detect closest_distances = self.knn.kneighbors(face_encodings, n_neighbors=1) AttributeError: 'NoneType' object has no attribute 'kneighbors'
from mlapi.
I also have a bunch of buggy events in zoneminder since updating mlapi. They seem to be registered just fine, just no video. Seems related due to timing.
Mvh.
Torkil
from mlapi.
Saving unknown faces seems to work like a charm though =)
Mvh.
from mlapi.
Please update all components (mlapi+ES+detection) and let me know if you still see this error
from mlapi.
Thanks, updated. Looking good so far =)
from mlapi.
There's this though:
"
Install Hook [y/N]:y
***** Installing Hooks **********
Checking for YoloV3 data files....
yolov3.cfg exists, no need to download
yolov3_classes.txt exists, no need to download
yolov3.weights exists, no need to download
Checking for TinyYOLO data files...
yolov3-tiny.cfg exists, no need to download
yolov3-tiny.txt exists, no need to download
yolov3-tiny.weights exists, no need to download
sudo: pip3: command not found
ERROR:python hooks setup failed
"
I know you don't like rookie questions but I can't see the problem. Pip3 is on my path.
from mlapi.
Maybe pip3 is not installed globally and when you do sudo itβs not found?
from mlapi.
I seriously dislike python packaging. You were right, so I just removed the sudo part from the install script and it ran. Thanks!
from mlapi.
Haven't seen the error with the new version.
from mlapi.
Related Issues (20)
- No timeout or no answer from coral Google TPU HOT 3
- Yolo v5 support HOT 1
- Support ML and stream sequences
- missing yolov3_classes.txt HOT 2
- remote ML requirements question HOT 6
- ValueError: malformed node or string: <_ast.Name object at 0x7f0e4cec2390> HOT 4
- show_percent=no not taken into account by mlapi HOT 6
- fix crappy ml_overrides approach from zm_detect to mlapi HOT 1
- platerecognizer chosen image quality HOT 2
- mlapi does not behave as ES does HOT 6
- mlapi crash on HOT 13
- RuntimeError: Internal: Unsupported data type in custom op handler HOT 2
- Unable to run mlapi as a service. Something to do with @jwt_required() HOT 4
- TypeError: 'float' object is not subscriptable HOT 2
- Issue with "Get an Access Token" HOT 6
- Error running model: invalid index to scalar variable. HOT 17
- ImportError: cannot import name 'soft_unicode' from 'markupsafe' HOT 1
- Dockerised version
- Secrets file is required, not optional HOT 1
- AttributeError: 'NoneType' object has no attribute 'get' HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
π 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. πππ
-
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 β€οΈ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from mlapi.