Comments (3)
I see the confusion. Yes, the total time is additive as in X plus Y.
When the --multi-gpu-testing
flag is used with {train,test}_net.py
inference happens on the dataset in a map-reduce way; the dataset is partitioned into NUM_GPUS
subsets and they are processed in parallel. Inference on each individual image is always run on a single GPU.
from detectron.
The explanation is correct; the "Y" time is indeed unoptimized CPU code. The fact that it's often so small is why it's left unoptimized :). The main point is that when considering how fast a model is, we can take the timing to be essentially just X because Y can be made much smaller with some engineering effort (e.g., the Y for Mask R-CNN is mostly time spent upsampling 100 predicted masks, one at a time, not in parallel; this could be replaced with a parallelized GPU implementation and take almost no time at all).
from detectron.
So, if I got this right, the total inference time is always X + Y, i.e. some parts of the inference is run on GPU, some on CPU? From the explanation I thought X is inference time on the GPU and Y is inference time on the CPU, i.e. the same algorithm on different hardware.. But I guess the "+" expresses exactly that :)
Does the inference time also relate to the hardware of
8 NVIDIA Tesla P100 GPU
, run in parallel?
from detectron.
Related Issues (20)
- the speed is slow
- 关于bbox损失函数部分,其中mask rcnn的λ权重平衡参数在哪啊 配置和代码里没看见啊。。。 HOT 1
- Detectron2 In-Place One-to-Many Augmentations HOT 2
- KeyError: u'Key TEST.SCALES was renamed to TEST.SCALE; please update your config. Note: Also convert from a tuple, e.g. (600, ), to a integer, e.g. 600.'
- libcaffe2_detectron_ops_gpu.so运行慢
- n/a
- How can I disable the logging system? HOT 1
- How to train Faster R-CNN on my own custom dataset? HOT 4
- Is there any script for batch inference?
- Detectron or Detection? HOT 1
- Project dependencies may have API risk issues
- Caffe 2 merged with pytorch new installation instruction?
- Convert Cityscapes to COCO format: How to convert to other classes (ex: traffic light) HOT 1
- detectron implantación inparcial,solicitud de inplantacion HOT 2
- Mask-RCNN model not properly generating segmentation masks for a specific class- custom dataset
- App etiquette HOT 2
- problem with adaptive streaming HOT 3
- why is threshold of detector confidence is 0.05, not 0.5? Helps, bros
- Really?
- Precision and recall (not AP not AR) values per class
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 detectron.