Comments (5)
Dear Rolf. It is true that the off-the-shelf version of MobileNetV2 might not be directly adequate for the D2 approach: as for ResNets, you would need to go to ~1/16th of input resolution to get a similar performance to the VGG counterpart. However, there are a few things that you could try:
-
As we did for VGG at test time, modifying the network to use dilated convolutions and no stride for the last block before the cut. This would get you to 1/8th of the resolution without any need for re-training.
-
To further improve the resolution, MobileNetV2 can be modified to obtain a lower stride. One could do this by either moving the strided convolutions at the end of each block (instead of the beginning) or by simply removing the stride of the first block. However, this would require re-training on ImageNet since the receptive fields of all layers would be completely different.
from d2-net.
Hello Mihai, thanks for the fast answer and the suggestions. I will try #1, and also test convolutional transpose. I'm shying back a bit from fully retraining MobileNet.
Have a nice day!
from d2-net.
Hi, @mihaidusmanu ,in the suplementary material it set K=4 for mining harder samples because the receptive field of conv_3 is 65x65 for VGG.However, doesn't it is 92x92 for conv4_3? so the K may be set 8?
from d2-net.
@Lakaemper Hi Lakaemper, I am working about trying to get D2 faster too. So I am wondering about werther it works with MobileNetV2. Thank you!
from d2-net.
I will close this issue since there are no recent updates. Feel free to re-open a new one if you run into any issues with the provided code.
from d2-net.
Related Issues (20)
- Issue with preprocessing undistorted images; overlap matrix can not be calculated HOT 2
- d2-net Feature extraction
- unable to download d2_tf.pth HOT 3
- Unable to download weight files! HOT 2
- D2Net model weights HOT 3
- please provide source code to export onnx file HOT 2
- Improving Performance on my dataset HOT 2
- Does the model_test need to train once again? HOT 3
- how to transfer keypoints get from d2-net to keypoint in opencv?I want to homography and perspectiveTransform operations
- Details about how to find correspondences in megadepth dataset
- -
- Failed to download models HOT 6
- MegaDepth saved npz poses as 1x4 array but should be 4x4 HOT 4
- undistorted reconstructions dataset link Error 404 HOT 2
- Question about the image undistortion HOT 1
- Undistorted and preprocessed images for our dataset HOT 1
- Uploading weights to Hugging Face
- Extracting features encountered RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cpu) HOT 1
- Error in model retraining parameters
- Inquiry about D2Net for Brain Tumor Segmentation on BraTS2018 Dataset 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 d2-net.