efficient ad #1128
Merged
efficient ad #1128
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
|
Hi Samuel, several comments:
|
|
@Idan-BenAmi should be good for review |
Idan-BenAmi
reviewed
Aug 20, 2024
| # * Uninfied version of model combining the three subversions | ||
| # ============================================================================== | ||
| """ | ||
| Yolov8n Object Detection Model - PyTorch implementation |
| sample, target = super().__getitem__(index) | ||
| return sample, target, path | ||
|
|
||
| def InfiniteDataloader(loader): |
There was a problem hiding this comment.
rename to snack case: infinite_dataloader
| sample, _ = super().__getitem__(index) | ||
| return sample | ||
|
|
||
| class ImageFolderWithPath(datasets.ImageFolder): |
There was a problem hiding this comment.
we already have a similar function, maybe can be reused..
| """Apply transformations to the training images.""" | ||
| return DEFAULT_TRANSFORM(image), DEFAULT_TRANSFORM(TRANSFORM_AE(image)) | ||
|
|
||
| def benchmark(unified_model, name): |
There was a problem hiding this comment.
I wonder if this code more isn't more suitable for "metric evaluation" folder.
| "\n", | ||
| "Anomaly detection models are useful as they only require your typical images to train and can in theory determin anything that is not typical.\n", | ||
| "\n", | ||
| "We use Efficient ad, one of the top performing anomaly detection models on the mvtec benchmark. benchmark leader board can be found [here](https://paperswithcode.com/sota/anomaly-detection-on-mvtec-ad)\n", |
There was a problem hiding this comment.
We use Efficient ad --> add link
on the mvtec benchmark --> add link (if available)
| "id": "tGqXJH15oLvm" | ||
| }, | ||
| "source": [ | ||
| "Download and extract the mvtec benchmark dataset. This is used for both training and evaluation. Link below is a direct linkk from the mcvtec website." |
There was a problem hiding this comment.
direct linkk -- >direct link
from the mcvtec website -- >add link
|
|
||
| This code contains a PyTorch implementation of efficient ad model, following | ||
| https://github.com/nelson1425/EfficientAD. This implementation includes a unified version of the model that combines the three submodels | ||
| into one to ease the process of quantisation and deployment. |
There was a problem hiding this comment.
quantisation --> quantization
| "source": [ | ||
| "Classification models are powerful and reliable, but what if you have little or no examples of one of your classes, what if one of your classes contains too much unpredictable variation?\n", | ||
| "\n", | ||
| "Here we go through the process of building, training and quantising an anomaly detection model designed to solve exactly these problems.\n", |
There was a problem hiding this comment.
quantising --> quantizing
| "id": "_fPTNtJLgPc5" | ||
| }, | ||
| "source": [ | ||
| "## Quantised model benchmark\n" |
There was a problem hiding this comment.
Quantised --> Quantized
| "source": [ | ||
| "## Conclusion\n", | ||
| "\n", | ||
| "In this notebook we provide examples on how to quantise and benchmark the latest anomaly detection model as well as providing code to visulize the models output." |
There was a problem hiding this comment.
quantise --> quantize
Idan-BenAmi
approved these changes
Aug 20, 2024
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.
Pull Request Description:
Addition of anomaly detection model
Checklist before requesting a review: