Comments (13)
No. PeleeNet is built with conventional convolution. Depthwise convolution can reduce the number of multi-add. But for the real speed, it depends on the devices and the framework you used. For example, both MobileNet+SSD and Pelee are much faster than TinyYOLO on CPU and iPhone6s, but TinyYOLO is slightly faster than Pelee on GTX 1080 Ti GPU and iPhone8. Although the number of multi-add of TinyYOLO is about 3 times larger than Pelee.
from pelee.
Most of the work in this paper was completed 8 months ago. At that time, except Tensorflow, other frameworks had bad support for Depthwise Separatable Convolution. However, the situation has changed a lot now. The performance of grouped convolution has improved greatly on cuDNNv7. Apple's CoreML also supports grouped convolution very well.
It is a good time to try the Depthwise Separatable Convolution version now. I am more interested in improving the accuracy by increasing the number of channels with Depthwise Separatable Convolution. Both MobileNet and PeleeNet can perform the image classification on iPhone6s, a phone released three years ago, in less than 50ms. The speed is good enough for many device-side applications.
from pelee.
Pelee detection on my RK3399, (2 Core- arm A72 at 1.8Ghz) takes 400ms for a frame.
So performance is not sufficient for my application (<100ms)
Thanks,
from pelee.
from pelee.
I use caffe framework and your pretrained model.
How do I check BN/Conv layer is merged or not?
Thanks,
from pelee.
According to the model you provided, in trian/test.prototxt
, the BN/Scale layer still exists alone. such as
layer {
name: "stem1/bn"
type: "BatchNorm"
bottom: "stem1"
top: "stem1"
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
param {
lr_mult: 0
decay_mult: 0
}
batch_norm_param {
moving_average_fraction: 0.999
eps: 0.001
}
}
layer {
name: "stem1/scale"
type: "Scale"
bottom: "stem1"
top: "stem1"
scale_param {
filler {
value: 1
}
bias_term: true
bias_filler {
value: 0
}
}
}
does this mean that conv layer and BN layer are not merged? If so, why is the inference time so fast?
The so-called "automatic merging BN layer with Conv layer", does it mean that we need to modify the underlying C++ code?
from pelee.
The models I provided are not merged. You can merge it by hand or other tools. I can add the merged model and script I used next week.
from pelee.
hope for your update
from pelee.
@Robert-JunWang Hi, I have two problems:
-
I found that you have uploaded a merged model, what is the principle of this? merged BN with convolution layer change original convolution calculation method?
-
In your paper, it says
we use a shallow and wide network structure to compensate for the negative impact on accuracy caused by this change
Is there any theoretical support for this? In general, a deeper network can bring higher accuracy.
from pelee.
Are you comparing the latency for your model with mobileNet SSD (without depthwise convolution)?
But mobileNet SSD could get 4 timers faster in GPU and 10 times faster in CPU with depthwise conv implementation. That means your model would be several times slower than mobileNet SSD with DW Conv...
from pelee.
Do you mean MobileNetV1+SSDlite is 10 times faster than MobileNetV1+SSD on CPU? Do you mind to offer more detail information on how you evaluate the speed and how to get that result? In my understanding, the computation cost of the SSD algorithm is mostly consumed by the backbone network. The real speed difference between SSDlite and the original SSD should not be that big.
from pelee.
As long as I understand the given merged models do not contain any batch normalization. Just convolution and ReLU, right?
from pelee.
mute
@Robert-JunWang what is the meaning of using half of the number of the dense layer with a doubled growth rate.can you show it and the map can fall much ?Thank you
from pelee.
Related Issues (20)
- fine tuning with different number of classes HOT 1
- peele-SSD add_extra_layers_pelee
- About the stanford dog dataset. HOT 3
- 2-way dense layer in code and paper seems mismatch. HOT 2
- how can i get the fps=120 on nvidia tx2? please help me HOT 1
- Calculation of number of parameter, macc, and flops HOT 3
- pytorch pretained model
- max_iter
- Does it support 512 or bigger input size? HOT 1
- question for iteration HOT 1
- can not download the pretrained PeleeNet model
- one question
- Question for peleeNet structure
- How can I train my own model?
- train error
- peleeNet speed in GTX1080ti HOT 1
- Question about 1x1 convolutional kernels to reduce computational cost
- the paper was accepted two years ago???
- Pelee input resolution problem
- question about merge bn?
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 pelee.