Comments (1)
I have the same problem, I have trained on 5 classes and 15 images each.
it always falsely predicts class 2.
I tried standard embeddings but the model is not discerning between brothers well. So I decided to try finetuning casia-webface/vggface2 and classifying with 4 classes and 1000 images each. I ran the fine tuning script and got .0001 losses for both train and val but when I test the model in production, I get strange performance as the returned tensor is usually argmax at index 3
tensor([[-111.6994, -166.2166, 496.6208, -121.9813]])
. When I train only the logits, the values are smallertensor([[ 1.9653, -2.2871, 6.6909, -6.1794]])
, but still falsely predicting class 3. Any clue what I may be doing wrong?
from facenet-pytorch.
Related Issues (20)
- Stopped working after upgrading pytorch from 1.11 to 1.12 HOT 2
- return None HOT 2
- Unexpected EOF Error for Resnet
- output embeddings dimension is weird HOT 1
- ONNX conversion HOT 3
- γ...'aten::nonzero' is not currently supported...γon M1
- Can not download the checkpoint in Remote Ubuntu machine
- Original FaceNet model? HOT 1
- how to github folder import HOT 1
- resize of non-square bounding boxes HOT 1
- ValueError with new numpy version for MTCNN HOT 5
- How to train and return 128 embedding? HOT 3
- memory leak in detect_face? HOT 3
- Extremely low LFW accuracy HOT 1
- MTCNN conversion to ONNX HOT 1
- Howo to recognize more than one face on one image? HOT 1
- A lot of false positives
- Wrong detected face saved
- image clustering according to the faces they contain
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
π 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. πππ
-
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 β€οΈ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from facenet-pytorch.