EfficientNet-PyTorch
A PyTorch implementation of EfficientNet and EfficientNetV2 (coming soon!) (by lukemelas)
DropoutUncertaintyExps
Experiments used in "Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning" (by yaringal)
Our great sponsors
EfficientNet-PyTorch | DropoutUncertaintyExps | |
---|---|---|
2 | 2 | |
7,715 | 519 | |
- | - | |
0.0 | 0.0 | |
about 2 years ago | about 2 years ago | |
Python | Python | |
Apache License 2.0 | GNU General Public License v3.0 or later |
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
EfficientNet-PyTorch
Posts with mentions or reviews of EfficientNet-PyTorch.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2022-03-02.
-
[D] MCDropout and CNNs
I used this with the popular pytorch implementation of EfficientNet. You can see what I'm talking about here https://github.com/lukemelas/EfficientNet-PyTorch/blob/master/efficientnet_pytorch/model.py on line 127. Once you understand this code it is pretty straightforward to modify your forward pass to allow "stochastic depth" during inference.
-
[P] Backprop: a library to easily finetune and use state-of-the-art models
I dont see you credit the author of https://github.com/lukemelas/EfficientNet-PyTorch yet you're using his implementation for efficientnet.
DropoutUncertaintyExps
Posts with mentions or reviews of DropoutUncertaintyExps.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2022-03-02.
-
[D] What is the current consensus on the effectiveness of Active Learning?
Code for https://arxiv.org/abs/1506.02142 found: https://github.com/yaringal/DropoutUncertaintyExps
-
[D] MCDropout and CNNs
I found a piece of code by Gal, who defines a log likelihood, and they use that to determine the best model: https://github.com/yaringal/DropoutUncertaintyExps/blob/master/net/net.py. Is that somewhat the standard approach?
What are some alternatives?
When comparing EfficientNet-PyTorch and DropoutUncertaintyExps you can also consider the following projects:
segmentation_models.pytorch - Segmentation models with pretrained backbones. PyTorch.
BIOBSS - A package for processing signals recorded using wearable sensors, such as Electrocardiogram (ECG), Photoplethysmogram (PPG), Electrodermal activity (EDA) and 3-axis acceleration (ACC).
MLclf - mini-imagenet and tiny-imagent dataset transformation for traditional classification task and also for the format for few-shot learning / meta-learning tasks
kiri - Backprop makes it simple to use, finetune, and deploy state-of-the-art ML models.