mirror of
https://github.com/Laurent2916/REVA-QCAV.git
synced 2024-11-09 15:02:03 +00:00
Add tensorboard.dev link in the README
Former-commit-id: d685fe10ac571e28e818a9d8fb19013e3346ee5f
This commit is contained in:
parent
d40a71737d
commit
2bef826dcc
|
@ -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.
|
The input images and target masks should be in the `data/imgs` and `data/masks` folders respectively.
|
||||||
|
|
||||||
## Tensorboard
|
## 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`
|
`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
|
## Notes on memory
|
||||||
|
|
||||||
The model has be trained from scratch on a GTX970M 3GB.
|
The model has be trained from scratch on a GTX970M 3GB.
|
||||||
|
|
Loading…
Reference in a new issue