-
pert_data.prepare_split(split = 'simulation_single', seed=1) # get data split with seed
pert_data.get_dataloader(batch_size = 32, test_batch_size = 128) # prepare data loader
This gives Value Erro…
-
In your paper——Unsupervised Deep Image Stitching: Reconstructing Stitched Features to Images ,V. EXPERIMENTS A. Dataset and Implement Details said,
To quantitatively describe the distribution of di…
-
* I think the figure could be improve to look sleeker
* the names of the project : our SAB recommended to have them all being "repro-something" - not sure a decision has been made yet there but sound…
-
### What happened + What you expected to happen
When I call `result.get_best_result('eval_accuracy', mode='max', scope='all')` I get the lowest metric score not the max metric score.
### Versions /…
-
Hi! Just wondering if FR-Perturb can be run on 1-guide 1-cell conventional Perturb-seq dataset?
Also do you have any suggestions for plotting UMAP for cell-guide pair that works/gets good perturbatio…
-
roachtest.perturbation/metamorphic/elasticWorkload [failed](https://teamcity.cockroachdb.com/buildConfiguration/Cockroach_Nightlies_RoachtestNightlyGceBazel/17460847?buildTab=log) with [artifacts](htt…
-
Given our example app that we're building, I was thinking that these are things we want to check off:
concepts to explain via first principles and thread into examples:
- [ ] - API call + knobs
…
-
In non-autonomous systems with parameter drift, long time averages are less useful to assess chaoticity.
There are several different ways to address this, one is related to the ensemble approach. H…
-
Machine learning models are often susceptible to adversarial perturbations of their inputs. Even small perturbations can cause state-of-the-art classifiers with high “standard” accuracy to produce an …
-
Hello,
I'm new to alibi and am loving it so far! I've been going through the Counterfactual Proto examples and wanted to ask how I could specify which input features should be perturbed for the co…