Comments (6)
akshitac8
commented on May 26, 2024
Hello @sbadirli, Thank you for your interest in our work.
Regarding the issue that you are facing, did you try reducing the learning rate?
from tfvaegan.
sbadirli
commented on May 26, 2024
Hi Akshita,
Thanks for replying back. Yes I tried the code with halving the learning
rate no luck. Should I further decrease the learning rate?
Thanks,
Sarkhan
…On Tue, Feb 23, 2021 at 6:19 AM Akshita Gupta ***@***.***> wrote:
Hello @sbadirli <https://github.com/sbadirli>, Thank you for your
interest in our work.
Regarding the issue that you are facing, did you try reducing the learning
rate?
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
<#9 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AGTKHA5S6AGCMDGSBK22RGTTAOFMHANCNFSM4XLPVAWA>
.
from tfvaegan.
akshitac8
commented on May 26, 2024
Hi @sbadirli,
Can you please check a few things with your training data?
- min and max of features does it have a nan value?
- Are there any images with empty labels in the dataset? if yes. can you remove them and then try training?
- Decrease the batch-size while training
- Decrease learning-rate
- Is this error coming in the beginning or after some epochs?
Regards,
Akshita
from tfvaegan.
sbadirli
commented on May 26, 2024
Hi Akshita,
Thank you so much for your detailed reply.
1. No
2. No
3. Will do that.
4. I did it and this time it worked till epoch 200. So this may help but it
will be hard to tune your method with this constraint. I will try my best
:)).
5. Previously with a large learning rate, it was at the beginning.
Best,
Sarkhan
…On Wed, Feb 24, 2021 at 3:03 AM Akshita Gupta ***@***.***> wrote:
Hi @sbadirli <https://github.com/sbadirli>,
Can you please check a few things with your training data?
1. min and max of features does it have a nan value?
2. Are there any images with empty labels in the dataset? if yes. can
you remove them and then try training?
3. Decrease the batch-size while training
4. Decrease learning-rate
5. Is this error coming in the beginning or after some epochs?
Regards,
Akshita
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
<#9 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AGTKHA2A4DHSMFN6CUQO243TASXF7ANCNFSM4XLPVAWA>
.
from tfvaegan.
akshitac8
commented on May 26, 2024
Hello @sbadirli, Is this issue solved?
from tfvaegan.
sbadirli
commented on May 26, 2024
Hi Akshita,
Yes, After lowering the learning rate the program did not give the same
problem, it is solved.
Thanks for your response and follow-up.
…On Mon, Mar 1, 2021 at 1:42 AM Akshita Gupta ***@***.***> wrote:
Hello @sbadirli <https://github.com/sbadirli>, Is this issue solved?
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
<#9 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AGTKHA4OQINKB52T3762KXDTBMZMVANCNFSM4XLPVAWA>
.
from tfvaegan.
Related Issues (20)
- There is problem with AWA2!! HOT 3
- ModuleNotFoundError: No module named 'util' HOT 1
- Transductive Setting HOT 6
- Recreating ResNet visual features HOT 3
- performance about CUB dataset HOT 7
- epoch 0 HOT 7
- classify HOT 5
- 'Variable' object has no attribute 'getLayersOutDet' HOT 7
- Transductive setting's hyperparameters HOT 1
- Model selection criteria HOT 4
- There is a gap in performance than in the paper HOT 7
- Question about argparse HOT 2
- Questions about training HOT 10
- What is the training unseen feature under transductive setting?
- Question about training on action recognition HOT 1
- About the loss in the training process HOT 3
- Question regarding fine-tuned features HOT 1
- role of parameter
- _test_unseen_feature = scaler.transform(feature[test_unseen_loc]) IndexError: index 382 is out of bounds for axis 0 with size 382
- Finetuned features MISS HOT 2
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 tfvaegan.