Comments (3)
A randomly seeded experiment should be completely possible. However, the fixed seed is necessary to recreate similar situations and repeatable experiments. I would suggest a random number generation scheme as input to the pbs script as opposed to completely removing or giving an option to avoid the seed. Let me know what you think.
from vip.
I agree with the rationale behind having the fixed seed as a capability, but I feel that the seed being random might be an expected capability (or even an expected behavior --- someone who doesn't read the yaml file too closely might not realize the random number generator is seeded by default).
I also think implementation would be very straightforward --- when the json is read, check if the seed is set to a designated "random" value. If so, set seed to the current timestamp.
from vip.
We are going to leave it up to the user to manually change the seed which can be automated using the --seed
argument. If you still want to remove the seed then you can comment out the line at the bottom of train.py
. There is currently a bug though that doesn't seed numpy so all of your experiments up to this point have been random anyway #25
from vip.
Related Issues (20)
- Change x-axis of validation accuracy HOT 1
- Seed Numpy in addition to Torch HOT 1
- Clip stride, clip offset, and num clips are unimplemented HOT 1
- Add preprocessing for x-y translation
- Variable clip length HOT 2
- Remove feature extraction code from c3d HOT 1
- Reset validation accuracy every epoch
- Add author accuracies in Readme
- Create outline for usage of ViP
- RuntimeError: Given input size: (512x1x7x7). Calculated output size: (512x0x4x4). Output size is too small HOT 1
- config error HOT 3
- Support for multi-gpu training & evaluation
- Pytorch definition of optimizers and schedulers
- Separate each metric and loss into files
- Change DataLoader Collate Function HOT 1
- About gen_json_UCF101 HOT 1
- Where should I put the dataset?
- Can you provide the link for 2.2 times cropped dataset of MPII+NZSL hand dataset? HOT 3
- No such file or directory: '/z/dat/HMDB51/train.json' 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 vip.