Comments (3)
Hi, any help for my problem. Thanks. The below is my training log. It is different with yours even at the very beginning. I wonder how to fix it. Thanks.
0 0 [0.2 0.21666667 0.22333333 0.27 0.25333333 0.26666667]
0 50 [0.20666667 0.23666667 0.24333333 0.25333333 0.27 0.27666667]
0 100 [0.20333333 0.23666667 0.27 0.27 0.28666667 0.29666667]
0 150 [0.27 0.30666667 0.33666667 0.32666667 0.32666667 0.30666667]
0 200 [0.25333333 0.26333333 0.29333333 0.28666667 0.30333333 0.31666667]
0 250 [0.25 0.28333333 0.3 0.34666667 0.32 0.31333333]
0 300 [0.24 0.31333333 0.36333333 0.41333333 0.42666667 0.43 ]
0 350 [0.21333333 0.33 0.40666667 0.41666667 0.41666667 0.39666667]
0 400 [0.17333333 0.33666667 0.36333333 0.38666667 0.39666667 0.4 ]
0 450 [0.21333333 0.25333333 0.26333333 0.28333333 0.29 0.28666667]
0 500 [0.23666667 0.29333333 0.34666667 0.38 0.4 0.42 ]
shuffle DB :test, b:600, 5-way, 1-shot, 15-query, resize:84
>>Test: [0.19648889 0.25035556 0.27977778 0.29324444 0.29655556 0.29744444] variance[K]: 0.0062 <<
0 550 [0.28 0.30666667 0.37 0.37 0.37333333 0.38666667]
0 600 [0.21 0.30666667 0.34666667 0.38666667 0.40666667 0.41666667]
0 650 [0.22333333 0.28666667 0.32333333 0.35666667 0.36 0.36666667]
0 700 [0.21333333 0.27666667 0.32666667 0.32333333 0.34 0.34666667]
0 750 [0.18666667 0.28333333 0.32 0.34 0.36 0.38666667]
0 800 [0.16666667 0.28 0.31333333 0.31333333 0.31666667 0.32333333]
0 850 [0.22333333 0.25 0.32666667 0.34666667 0.34333333 0.34666667]
0 900 [0.23 0.32333333 0.39 0.40333333 0.41333333 0.42 ]
0 950 [0.21333333 0.32666667 0.36333333 0.37 0.37 0.37333333]
0 1000 [0.28 0.37666667 0.44333333 0.45333333 0.46333333 0.48 ]
shuffle DB :test, b:600, 5-way, 1-shot, 15-query, resize:84
>>Test: [0.16908889 0.23284444 0.27973333 0.29833333 0.30786667 0.31355556] variance[K]: 0.0067 <<
from maml-pytorch.
Hi, Maybe you can modify the line: if training:
to if True:
.
Line 399 in 69c08a0
and it should work as the readme file.
Indeed, someone found the code includes a potential bugs from: #6
so you can try and see any solutions.
from maml-pytorch.
Thanks for the reply. I also ran the original Tensorflow version provided by the authors. The results seems fine. Maybe we can check step by step by comparing the intermediate results generated. Please update the code if you find the bug. Thanks for your effort.
from maml-pytorch.
Related Issues (20)
- why use custom grad clip function?
- omniglot dataset download error HOT 1
- Does the hessian really gets computed? HOT 1
- Can you please add a 1-d CNN model to the learner.
- Incorrect losses_q HOT 3
- about dataset spiltting
- create_graph parameter is False hence first-order MAML? HOT 1
- Asking about inner and outer loop
- 您好,对于代码有两个问题,请教您一下,谢谢 HOT 3
- About training and testing HOT 6
- can you offer us your requirements of environment?
- Why is `for epoch in range(args.epoch // 10000):` HOT 2
- Why the code for Learner is so complicated? HOT 1
- 请问模型权值文件在哪里进行保存?代码在哪里? HOT 1
- debug
- Using the Learner object for my project, Loss not behaving at its best
- About accuracy HOT 6
- What is the backup file for and what is the reference navie5 in navie5?
- 准确率不变 HOT 4
- 训练自己的数据集
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 maml-pytorch.