🔨 Increase inference + openvino support #122
Merged
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
samet-akcay
reviewed
Feb 28, 2022
samet-akcay
reviewed
Feb 28, 2022
anomalib/models/dfkde/model.py
Outdated
| layer_outputs = torch.cat(list(layer_outputs.values())).detach() | ||
| return layer_outputs | ||
|
|
||
| def fit_normality_model(self, embeddings: List[Tensor]): |
There was a problem hiding this comment.
i would prefer this is called just fit. During its usage, it would just be self.model.fit(embeddings
samet-akcay
reviewed
Feb 28, 2022
djdameln
requested changes
Mar 2, 2022
anomalib/models/dfkde/model.py
Outdated
|
|
||
| from anomalib.models.components import AnomalyModule, FeatureExtractor | ||
|
|
||
| from .normality_model import NormalityModel | ||
|
|
||
|
|
||
| class DfkdeModel(nn.Module): | ||
| """DFKDR model. |
anomalib/models/dfkde/model.py
Outdated
| feature_vector = self.get_features(batch) | ||
| return self.normality_model.predict(feature_vector.view(feature_vector.shape[:2])) | ||
|
|
||
|
|
||
| class DfkdeLightning(AnomalyModule): | ||
| """DFKDE: Deep Featured Kernel Density Estimation. |
anomalib/models/dfkde/model.py
Outdated
| filter_count=hparams.model.max_training_points, | ||
| threshold_steepness=self.threshold_steepness, | ||
| threshold_offset=self.threshold_offset, | ||
| backbone = getattr(torchvision.models, hparams.model.backbone) |
There was a problem hiding this comment.
Maybe you could create the backbone inside DfkdeModel and just pass the hparams.model.backbone to the constructor of that class. That would be more in line with other models (see Padim for example).
anomalib/models/dfm/model.py
Outdated
| self.feature_extractor = FeatureExtractor(backbone=self.backbone(pretrained=True), layers=["avgpool"]).eval() | ||
|
|
||
| self.dfm_model = DFMModel(n_comps=hparams.model.pca_level, score_type=hparams.model.score_type) | ||
| backbone = getattr(torchvision.models, hparams.model.backbone) |
There was a problem hiding this comment.
Same here, let's pass the string from the hparams and then instantiate the backbone inside the pytorch model.
djdameln
approved these changes
Mar 8, 2022
samet-akcay
approved these changes
Mar 8, 2022
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.
Description
Increases inferencer support to all models and openvino support to ganomaly and dfm.
Fixes Ganomaly inference.py error #97
Known Issues
Changes
Checklist
Tests