Comments (5)
WalterMa
commented on May 30, 2024
Overfit？
Or try to use ROI Align replace ROI Pooling？
Ram124 <[email protected]> 于2018年10月22日周一 下午5:59写道：
… Hello,
I have trained the model with the given configs. But i am getting only 80%
accuracy on 2 object class data.
Is there any possibility to increase it further?? What parameters should i
change to increase the accuracy??
I am using mobilenet 0.25 version as base network..
—
You are receiving this because you are subscribed to this thread.
Reply to this email directly, view it on GitHub
<#8>, or mute the
thread
<https://github.com/notifications/unsubscribe-auth/AHNbxBd2tNIOVVTht9xBUVi0VFuQSbRYks5unZccgaJpZM4XzEVv>
.
from gluon-faster-rcnn.
Ram-Godavarthi
commented on May 30, 2024
@WalterMa
Should i include that in the mobilenet.py in rcnn/base_model by replacing the below line
x = F.ROIPooling(data=feature_map, rois=rois, pooled_size=(7, 7), spatial_scale=1.0 / self.feature_stride)
as
x = F.ROIalign(data=feature_map, rois=rois, pooled_size=(7, 7), spatial_scale=1.0 / self.feature_stride)
Is this correct??
from gluon-faster-rcnn.
WalterMa
commented on May 30, 2024
Yes
refer to
https://mxnet.incubator.apache.org/api/python/symbol/contrib.html?highlight=roi#mxnet.symbol.contrib.ROIAlign
Ram124 <[email protected]> 于2018年10月25日周四 下午5:56写道：
… @WalterMa <https://github.com/WalterMa>
Should i include that in the mobilenet.py in rcnn/base_model by replacing
the below line
x = F.ROIPooling(data=feature_map, rois=rois, pooled_size=(7, 7),
spatial_scale=1.0 / self.feature_stride)
as
x = F.ROIalign(data=feature_map, rois=rois, pooled_size=(7, 7),
spatial_scale=1.0 / self.feature_stride)
Is this correct??
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
<#8 (comment)>,
or mute the thread
<https://github.com/notifications/unsubscribe-auth/AHNbxIEdHNlySDJbocfBXyjCoSloMpzJks5uoYrcgaJpZM4XzEVv>
.
from gluon-faster-rcnn.
Ram-Godavarthi
commented on May 30, 2024
Can I use the already trained .params files to use the weights ??
I have changed the cfg.resume to True.
But it is throwing an error due rcnnhead layers.
I am using 3 layers in rcnnhead. how to initialize them??
only base network layers are initialized from .params file.
the error is : conv13 is not initialized. (conv13 is in rcnnhead)
from gluon-faster-rcnn.
WalterMa
commented on May 30, 2024
Yes.
I have already tested on vgg16, that I could resume training from saved params.
So I'm not sure about reasons of your problem.
from gluon-faster-rcnn.
Related Issues (9)
- Could you share the training log of your faster rcnn(vgg16)? HOT 2
- Could you share the pre-trained model parameters? HOT 3
- Working on Windows with same accuracy HOT 11
- Working with different base net HOT 8
- Issue with demo_faster_rcnn.py script. HOT 9
- How does C++ call the model HOT 2
- Regarding testing accuracy and class score values
- network is not learning if not hybridized HOT 1
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 gluon-faster-rcnn.