Comments (9)
The entire script takes about 400ms for me to run, and the actual inference step y = net(x)
takes about 70ms. The infer.py
script never calls .cuda()
so everything is running on CPU. I tried moving it to the GPU, but that just makes the single inference slower (takes longer to move the single image on and off the GPU); ends up being 16 seconds, with 5 seconds on inference.
from shufflenet.
For completeness, I was running with pytorch version 0.4.0, and pip freeze
gave this. I installed the conda env following the instructions to build pytorch from source.
Also, here are the CPU details:
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Byte Order: Little Endian
CPU(s): 32
On-line CPU(s) list: 0-31
Thread(s) per core: 2
Core(s) per socket: 8
Socket(s): 2
NUMA node(s): 2
Vendor ID: GenuineIntel
CPU family: 6
Model: 79
Model name: Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
Stepping: 1
CPU MHz: 1200.281
With an old conda env on pytorch version 0.2.0, it took 150ms for inference and 350ms for the whole script.
from shufflenet.
Hmm okay. I guess there's no need to improve speed if it works well enough. I'll figure out what the problem is on my end.
from shufflenet.
Hi @ildoonet, I'll take a look when I get time :)
from shufflenet.
I finally got around to doing some inference on ShuffleNet today. And it is definitely far too slow. Any ideas on how to speed it up? I suspect the snail-like speed is due to the frequent channel shuffling.
from shufflenet.
@gngdb if you have any ideas on how to speed it up in PyTorch, would love to know. I can't imagine doing a full training run at this speed. Speeding up would drastically help you with training too
from shufflenet.
What version of PyTorch are you running? The speed of grouped convolutions increased a lot in the most recent versions.
from shufflenet.
I'm running PyTorch 0.3.0 with CUDA. How long does it take for you to do one inference on the cat image? It takes probably 30 seconds for me.
from shufflenet.
@jaxony HI,have you solved it?
from shufflenet.
Related Issues (12)
- batch normalization and relu after first conv HOT 1
- maybe a mistake
- Steps to run shuffle net on imagenet dataset.
- Wrong number of channels for g=1, stage4: should be 576, not 567
- load_state_dict while errors occurs
- the pretrained state dictionary
- Train/Test Speed HOT 2
- Question about the out_channels HOT 2
- When group=8, input channels cannot be divided by group number HOT 2
- ImageNet result HOT 21
- Pretrained Model Cannot Be Opened HOT 3
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 shufflenet.