Add SwaV self-supervision method #197
Open
Conversation
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
VladVin
requested changes
May 10, 2023
| multi_crop_features = [self.forward(crop) for crop in crops] | ||
| high_resolution = multi_crop_features[:self.num_highres_crops] | ||
| low_resolution = multi_crop_features[self.num_highres_crops:] | ||
| output = {"high_resolution": high_resolution, "low_resolution": low_resolution} |
There was a problem hiding this comment.
Let's rename to high_resolution_embs, low_resolution_logits
torchok/data/transforms/swav.py
Outdated
| cj_contrast: How much to jitter contrast. | ||
| cj_sat: How much to jitter saturation. | ||
| cj_hue: How much to jitter hue. | ||
| random_gray_scale: Probability of conversion to grayscale. |
There was a problem hiding this comment.
May be to rename in the same fashion, i.e. gray_prob?
torchok/data/transforms/swav.py
Outdated
| cj_sat: How much to jitter saturation. | ||
| cj_hue: How much to jitter hue. | ||
| random_gray_scale: Probability of conversion to grayscale. | ||
| gaussian_blur: Probability of Gaussian blur. |
torchok/data/transforms/utils.py
Outdated
| "Length of crop_sizes and crop_min_scales must be equal but are" | ||
| f" {len(crop_sizes)} and {len(crop_min_scales)}." | ||
| ) | ||
| if len(crop_sizes) != len(crop_min_scales): |
There was a problem hiding this comment.
There must be crop_max_scales, fixed
|
|
||
| for j in range(num_views): | ||
| cross_batch_view = default_collate([sample_views[j] for sample_views in batch]) | ||
| for k, v in cross_batch_view.items(): |
There was a problem hiding this comment.
Please, rename k and v within this class to easier read the code
|
|
||
| return new_samples | ||
|
|
||
| def collate_fn(self, batch: List[List[Dict[str, Any]]]) -> Dict[str, List[torch.Tensor]]: |
There was a problem hiding this comment.
Describe what is on input and on output
| p = self.prototypes(x) | ||
| return p | ||
|
|
||
| def forward_with_gt(self, batch: Dict[str, Tensor]) -> Dict[str, List[Tensor]]: |
There was a problem hiding this comment.
Is the batch typing correct?
|
|
||
|
|
||
| @TASKS.register_class | ||
| class SwaVTask(ClassificationTask): |
There was a problem hiding this comment.
Can you add an example config for this task?
There was a problem hiding this comment.
I will add later when i get the same results as lightly
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.