-
Notifications
You must be signed in to change notification settings - Fork 21
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
updating run.sh to only run n2d.
- Loading branch information
Showing
1 changed file
with
12 additions
and
12 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,16 +1,16 @@ | ||
| # Evaluate only n2d | ||
| #python n2d.py mnist 0 --ae_weights=mnist-1000-ae_weights.h5 --umap_dim=10 --umap_neighbors=20 --manifold_learner=UMAP --save_dir=mnist-n2d --umap_min_dist=0.00 | ||
| #python n2d.py fashion 0 --ae_weights=fashion-1000-ae_weights.h5 --umap_dim=10 --umap_neighbors=20 --manifold_learner=UMAP --save_dir=fashion-n2d --umap_min_dist=0.00 | ||
| #python n2d.py mnist-test 0 --ae_weights=mnist-test-1000-ae_weights.h5 --umap_dim=10 --umap_neighbors=20 --manifold_learner=UMAP --save_dir=mnist-test-n2d --umap_min_dist=0.00 | ||
| #python n2d.py usps 0 --ae_weights=usps-1000-ae_weights.h5 --umap_dim=10 --umap_neighbors=20 --manifold_learner=UMAP --save_dir=usps-n2d --umap_min_dist=0.00 | ||
| #python n2d.py pendigits 0 --ae_weights=pendigits-1000-ae_weights.h5 --umap_dim=10 --umap_neighbors=20 --manifold_learner=UMAP --save_dir=pendigits-n2d --umap_min_dist=0.00 | ||
| #python n2d.py har 0 --ae_weights=har-1000-ae_weights.h5 --umap_dim=6 --umap_neighbors=20 --manifold_learner=UMAP --save_dir=har-n2d --umap_min_dist=0.00 --n_clusters=6 | ||
| python n2d.py mnist 0 --ae_weights=mnist-1000-ae_weights.h5 --umap_dim=10 --umap_neighbors=20 --manifold_learner=UMAP --save_dir=mnist-n2d --umap_min_dist=0.00 | ||
| python n2d.py fashion 0 --ae_weights=fashion-1000-ae_weights.h5 --umap_dim=10 --umap_neighbors=20 --manifold_learner=UMAP --save_dir=fashion-n2d --umap_min_dist=0.00 | ||
| python n2d.py mnist-test 0 --ae_weights=mnist-test-1000-ae_weights.h5 --umap_dim=10 --umap_neighbors=20 --manifold_learner=UMAP --save_dir=mnist-test-n2d --umap_min_dist=0.00 | ||
| python n2d.py usps 0 --ae_weights=usps-1000-ae_weights.h5 --umap_dim=10 --umap_neighbors=20 --manifold_learner=UMAP --save_dir=usps-n2d --umap_min_dist=0.00 | ||
| python n2d.py pendigits 0 --ae_weights=pendigits-1000-ae_weights.h5 --umap_dim=10 --umap_neighbors=20 --manifold_learner=UMAP --save_dir=pendigits-n2d --umap_min_dist=0.00 | ||
| python n2d.py har 0 --ae_weights=har-1000-ae_weights.h5 --umap_dim=6 --umap_neighbors=20 --manifold_learner=UMAP --save_dir=har-n2d --umap_min_dist=0.00 --n_clusters=6 | ||
|
|
||
| # Evaluate a number of approaches (including baselines) | ||
| python n2d.py mnist 0 --ae_weights=mnist-1000-ae_weights.h5 --umap_dim=2 --umap_neighbors=20 --manifold_learner=UMAP --save_dir=mnist-n2d-viz --umap_min_dist=0.00 --visualize --eval_all | ||
| python n2d.py fashion 0 --ae_weights=fashion-1000-ae_weights.h5 --umap_dim=2 --umap_neighbors=20 --manifold_learner=UMAP --save_dir=fashion-n2d-viz --umap_min_dist=0.00 --visualize --eval_all | ||
| python n2d.py mnist-test 0 --ae_weights=mnist-test-1000-ae_weights.h5 --umap_dim=2 --umap_neighbors=20 --manifold_learner=UMAP --save_dir=mnist-test-n2d-viz --umap_min_dist=0.00 --visualize --eval_all | ||
| python n2d.py usps 0 --ae_weights=usps-1000-ae_weights.h5 --umap_dim=2 --umap_neighbors=20 --manifold_learner=UMAP --save_dir=usps-n2d-viz --umap_min_dist=0.00 --visualize --eval_all | ||
| python n2d.py pendigits 0 --ae_weights=pendigits-1000-ae_weights.h5 --umap_dim=2 --umap_neighbors=20 --manifold_learner=UMAP --save_dir=pendigits-n2d-viz --umap_min_dist=0.00 --visualize --eval_all | ||
| python n2d.py har 0 --ae_weights=har-1000-ae_weights.h5 --umap_dim=2 --umap_neighbors=20 --manifold_learner=UMAP --save_dir=har-n2d-viz --umap_min_dist=0.00 --n_clusters=6 --visualize --eval_all | ||
| #python n2d.py mnist 0 --ae_weights=mnist-1000-ae_weights.h5 --umap_dim=2 --umap_neighbors=20 --manifold_learner=UMAP --save_dir=mnist-n2d-viz --umap_min_dist=0.00 --visualize --eval_all | ||
| #python n2d.py fashion 0 --ae_weights=fashion-1000-ae_weights.h5 --umap_dim=2 --umap_neighbors=20 --manifold_learner=UMAP --save_dir=fashion-n2d-viz --umap_min_dist=0.00 --visualize --eval_all | ||
| #python n2d.py mnist-test 0 --ae_weights=mnist-test-1000-ae_weights.h5 --umap_dim=2 --umap_neighbors=20 --manifold_learner=UMAP --save_dir=mnist-test-n2d-viz --umap_min_dist=0.00 --visualize --eval_all | ||
| #python n2d.py usps 0 --ae_weights=usps-1000-ae_weights.h5 --umap_dim=2 --umap_neighbors=20 --manifold_learner=UMAP --save_dir=usps-n2d-viz --umap_min_dist=0.00 --visualize --eval_all | ||
| #python n2d.py pendigits 0 --ae_weights=pendigits-1000-ae_weights.h5 --umap_dim=2 --umap_neighbors=20 --manifold_learner=UMAP --save_dir=pendigits-n2d-viz --umap_min_dist=0.00 --visualize --eval_all | ||
| #python n2d.py har 0 --ae_weights=har-1000-ae_weights.h5 --umap_dim=2 --umap_neighbors=20 --manifold_learner=UMAP --save_dir=har-n2d-viz --umap_min_dist=0.00 --n_clusters=6 --visualize --eval_all | ||
|
|