Comments (4)
Thanks, VS for the great reproducer!
I've root caused and fixed the issue. The reason isn't mixed-precision initialization, but quantization metrics collection on each train iteration.
for stat_name, stat_value in compression_ctrl.statistics().items():
if isinstance(stat_value, (int, float)):
Starting from #33 it takes a lot of time.
Here's the fix - #287
After the fix, 1 epoch takes 52 min with RTX-2080, instead of 76 min before.
from nncf.
@vuiseng9 are you sure that torch 1.6.2 was used? We automatically install 1.5.0 by default (not reinstalling it, though, if a newer version is already present, AFAIK)
from nncf.
@vshampor Sorry, it is a typo, it is 1.6.0. I notice torch version will be different if we install python setup.py install
vs pip install -r requirements.txt
from nncf.
@vuiseng9 @ljaljushkin is this still actual?
from nncf.
Related Issues (20)
- yolov8+nncf error HOT 5
- about saved model after quantization HOT 4
- cuda HOT 1
- bounds incompatible with pandas 2.1.4 HOT 1
- AttributeError: 'SymmetricQuantizer' object has no attribute 'register_load_state_dict_post_hook'
- SensitivityMetric is not available in nncf namespace HOT 1
- [BUG] Returning the input to an Upsample layer crashes `nncf.quantize` HOT 2
- Compressed models that call torch.is_floating_point() during inference are traced with runtime error.
- nncf + ultralytics yolov8 training-time compression HOT 7
- Ultralytics yolov8 QAT example HOT 1
- [Good First Issue] [NNCF] Make NNCF common utils code pass mypy checks HOT 23
- [Good First Issue] [NNCF] Make NNCF common accuracy aware training code pass mypy checks HOT 17
- [Good First Issue] [NNCF] Make NNCF common tensor statistics code pass mypy checks HOT 9
- [Good First Issue] [NNCF] Make NNCF common pruning code pass mypy checks HOT 14
- [Good First Issue] [NNCF] Make NNCF common graph code pass mypy checks HOT 26
- [Good First Issue] [NNCF] Cover NNCF code with least coverage percentage with unit tests to at least 80% HOT 25
- [Good First Issue] [NNCF] Make NNCF common sparsity code pass mypy checks HOT 6
- [Good First Issue] [NNCF] Introduce NNCF-specific exception classes across NNCF code base for expected/avoidable error cases instead of standard `RuntimeError` HOT 5
- Thanks to our Contributors HOT 1
- [Good First Issue][NNCF]: Add INT8 weight compression conformance test for Tinyllama-1.1b PyTorch model HOT 19
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 nncf.