ENSEEIHT/projet-long
1
0
Fork 0
Code Issues Pull requests Packages Projects Releases Wiki Activity

Add tensorboard.dev link in the README

Browse source 
Former-commit-id: d685fe10ac571e28e818a9d8fb19013e3346ee5f
This commit is contained in:
milesial 2020-03-15 22:37:20 -07:00
parent d40a71737d
commit 2bef826dcc
1 changed files with 3 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
README.md
View file

@ -79,10 +79,12 @@ By default, the `scale` is 0.5, so if you wish to obtain better results (but use
The input images and target masks should be in the `data/imgs` and `data/masks` folders respectively.
## Tensorboard
You can visualize in real time the train and test losses, along with the model predictions with tensorboard:
You can visualize in real time the train and test losses, the weights and gradients, along with the model predictions with tensorboard:
`tensorboard --logdir=runs`
You can find a reference training run with the Caravana dataset on [TensorBoard.dev](https://tensorboard.dev/experiment/1m1Ql50MSJixCbG1m9EcDQ/#scalars&_smoothingWeight=0.6) (only scalars are shown currently).
## Notes on memory
The model has be trained from scratch on a GTX970M 3GB.