Skip to content

Commit

Permalink
⏳ Restore Images (#1791)
Browse files Browse the repository at this point in the history
Restore images

Signed-off-by: Ashwin Vaidya <[email protected]>
  • Loading branch information
ashwinvaidya17 authored Feb 28, 2024
1 parent 2fc5a13 commit fa5ac1a
Show file tree
Hide file tree
Showing 45 changed files with 46 additions and 50 deletions.
Binary file added docs/source/images/cfa/architecture.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added docs/source/images/cfa/results/0.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added docs/source/images/cfa/results/1.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added docs/source/images/cfa/results/2.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added docs/source/images/cflow/architecture.jpg
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added docs/source/images/cflow/results/0.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added docs/source/images/cflow/results/1.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added docs/source/images/cflow/results/2.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added docs/source/images/cs_flow/architecture1.jpg
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added docs/source/images/cs_flow/architecture2.jpg
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added docs/source/images/cs_flow/architecture3.jpg
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added docs/source/images/draem/architecture.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added docs/source/images/fastflow/architecture.jpg
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added docs/source/images/fastflow/results/0.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added docs/source/images/fastflow/results/1.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added docs/source/images/fastflow/results/2.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added docs/source/images/ganomaly/architecture.jpg
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added docs/source/images/padim/architecture.jpg
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added docs/source/images/padim/results/0.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added docs/source/images/padim/results/1.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added docs/source/images/padim/results/2.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added docs/source/images/patchcore/architecture.jpg
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added docs/source/images/patchcore/results/0.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added docs/source/images/patchcore/results/1.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added docs/source/images/patchcore/results/2.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file added docs/source/images/stfpm/architecture.jpg
Binary file added docs/source/images/stfpm/results/0.png
Binary file added docs/source/images/stfpm/results/1.png
Binary file added docs/source/images/stfpm/results/2.png
8 changes: 4 additions & 4 deletions src/anomalib/models/image/cfa/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,7 @@ Coupled-hypersphere-based Feature Adaptation (CFA) localizes anomalies using fea

## Architecture

![Cfa Architecture](https://raw.githubusercontent.com/openvinotoolkit/anomalib/main/docs/source/images/cfa/architecture.png "Cfa Architecture")
![Cfa Architecture](../../../../../docs/source/images/cfa/architecture.png "Cfa Architecture")

## Usage

Expand Down Expand Up @@ -139,11 +139,11 @@ When the numbers are produced, early stopping callback (patience: 5) is used. It

### Sample Results

![Sample Result 1](../../../../docs/source/images/cfa/results/0.png "Sample Result 1")
![Sample Result 1](../../../../../docs/source/images/cfa/results/0.png "Sample Result 1")

![Sample Result 2](../../../../docs/source/images/cfa/results/1.png "Sample Result 2")
![Sample Result 2](../../../../../docs/source/images/cfa/results/1.png "Sample Result 2")

![Sample Result 3](../../../../docs/source/images/cfa/results/2.png "Sample Result 3")
![Sample Result 3](../../../../../docs/source/images/cfa/results/2.png "Sample Result 3")

## Reference

Expand Down
8 changes: 4 additions & 4 deletions src/anomalib/models/image/cflow/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@ CFLOW model is based on a conditional normalizing flow framework adopted for ano

## Architecture

![CFlow Architecture](https://raw.githubusercontent.com/openvinotoolkit/anomalib/main/docs/source/images/cflow/architecture.jpg "CFlow Architecture")
![CFlow Architecture](../../../../../docs/source/images/cflow/architecture.jpg "CFlow Architecture")

## Usage

Expand Down Expand Up @@ -42,8 +42,8 @@ All results gathered with seed `42`.

### Sample Results

![Sample Result 1](../../../../docs/source/images/cflow/results/0.png "Sample Result 1")
![Sample Result 1](../../../../../docs/source/images/cflow/results/0.png "Sample Result 1")

![Sample Result 2](../../../../docs/source/images/cflow/results/1.png "Sample Result 2")
![Sample Result 2](../../../../../docs/source/images/cflow/results/1.png "Sample Result 2")

![Sample Result 3](../../../../docs/source/images/cflow/results/2.png "Sample Result 3")
![Sample Result 3](../../../../../docs/source/images/cflow/results/2.png "Sample Result 3")
12 changes: 4 additions & 8 deletions src/anomalib/models/image/csflow/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -23,11 +23,11 @@ The anomaly score for each local position $(i,j)$ of the feature map $y^s$ at sc

## Architecture

![CS-Flow Architecture](https://raw.githubusercontent.com/openvinotoolkit/anomalib/main/docs/source/images/cs_flow/architecture1.jpg "CS-Flow Architecture")
![CS-Flow Architecture](../../../../../docs/source/images/cs_flow/architecture1.jpg "CS-Flow Architecture")

![Architecture of a Coupling Block](https://raw.githubusercontent.com/openvinotoolkit/anomalib/main/docs/source/images/cs_flow/architecture2.jpg "Architecture of a Coupling Block")
![Architecture of a Coupling Block](../../../../../docs/source/images/cs_flow/architecture2.jpg "Architecture of a Coupling Block")

![Architecture of network predicting scale and shift parameters.](https://raw.githubusercontent.com/openvinotoolkit/anomalib/main/docs/source/images/cs_flow/architecture3.jpg "Architecture of network predicting scale and shift parameters.")
![Architecture of network predicting scale and shift parameters.](../../../../../docs/source/images/cs_flow/architecture3.jpg "Architecture of network predicting scale and shift parameters.")

## Usage

Expand Down Expand Up @@ -93,8 +93,4 @@ All results gathered with seed `42`.

### Sample Results

![Sample Result 1](../../../../docs/source/images/csflow/results/0.png "Sample Result 1")

![Sample Result 2](../../../../docs/source/images/csflow/results/1.png "Sample Result 2")

![Sample Result 3](../../../../docs/source/images/csflow/results/2.png "Sample Result 3")
### TODO: Add results
4 changes: 2 additions & 2 deletions src/anomalib/models/image/draem/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -12,12 +12,12 @@ For optimal results, DRAEM requires specifying the path to a folder of image dat

## Architecture

![DRAEM Architecture](https://raw.githubusercontent.com/openvinotoolkit/anomalib/main/docs/source/images/draem/architecture.png "DRAEM Architecture")
![DRAEM Architecture](../../../../../docs/source/images/draem/architecture.png "DRAEM Architecture")

## Usage

`python tools/train.py --model draem`

## Benchmark

Benchmarking results are not yet available for this algorithm. Please check again later.
### TODO: Add results + benchmark
2 changes: 1 addition & 1 deletion src/anomalib/models/image/dsr/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@ DSR is a quantized-feature based algorithm that consists of an autoencoder with

## Architecture

![DSR Architecture](https://raw.githubusercontent.com/openvinotoolkit/anomalib/main/docs/source/images/dsr/architecture.png "DSR Architecture")
![DSR Architecture](../../../../../docs/source/images/dsr/architecture.png "DSR Architecture")

## Usage

Expand Down
8 changes: 4 additions & 4 deletions src/anomalib/models/image/fastflow/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@ FastFlow is a two-dimensional normalizing flow-based probability distribution es

## Architecture

![FastFlow Architecture](https://raw.githubusercontent.com/openvinotoolkit/anomalib/main/docs/source/images/fastflow/architecture.jpg "FastFlow Architecture")
![FastFlow Architecture](../../../../../docs/source/images/fastflow/architecture.jpg "FastFlow Architecture")

## Usage

Expand Down Expand Up @@ -110,8 +110,8 @@ All results gathered with seed `0`.

### Sample Results

![Sample Result 1](../../../../docs/source/images/fastflow/results/0.png "Sample Result 1")
![Sample Result 1](../../../../../docs/source/images/fastflow/results/0.png "Sample Result 1")

![Sample Result 2](../../../../docs/source/images/fastflow/results/1.png "Sample Result 2")
![Sample Result 2](../../../../../docs/source/images/fastflow/results/1.png "Sample Result 2")

![Sample Result 3](../../../../docs/source/images/fastflow/results/2.png "Sample Result 3")
![Sample Result 3](../../../../../docs/source/images/fastflow/results/2.png "Sample Result 3")
2 changes: 1 addition & 1 deletion src/anomalib/models/image/ganomaly/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,7 @@ The key idea here is that, during inference, when an anomalous image is passed t

## Architecture

![GANomaly Architecture](https://raw.githubusercontent.com/openvinotoolkit/anomalib/main/docs/source/images/ganomaly/architecture.jpg "GANomaly Architecture")
![GANomaly Architecture](../../../../../docs/source/images/ganomaly/architecture.jpg "GANomaly Architecture")

## Usage

Expand Down
8 changes: 4 additions & 4 deletions src/anomalib/models/image/padim/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,7 @@ During inference, Mahalanobis distance is used to score each patch position of t

## Architecture

![PaDiM Architecture](https://raw.githubusercontent.com/openvinotoolkit/anomalib/main/docs/source/images/padim/architecture.jpg "PaDiM Architecture")
![PaDiM Architecture](../../../../../docs/source/images/padim/architecture.jpg "PaDiM Architecture")

## Usage

Expand Down Expand Up @@ -47,8 +47,8 @@ All results gathered with seed `42`.

### Sample Results

![Sample Result 1](../../../../docs/source/images/padim/results/0.png "Sample Result 1")
![Sample Result 1](../../../../../docs/source/images/padim/results/0.png "Sample Result 1")

![Sample Result 2](../../../../docs/source/images/padim/results/1.png "Sample Result 2")
![Sample Result 2](../../../../../docs/source/images/padim/results/1.png "Sample Result 2")

![Sample Result 3](../../../../docs/source/images/padim/results/2.png "Sample Result 3")
![Sample Result 3](../../../../../docs/source/images/padim/results/2.png "Sample Result 3")
8 changes: 4 additions & 4 deletions src/anomalib/models/image/patchcore/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,7 @@ During inference this memory bank is coreset subsampled. Coreset subsampling gen

## Architecture

![PatchCore Architecture](https://raw.githubusercontent.com/openvinotoolkit/anomalib/main/docs/source/images/patchcore/architecture.jpg "PatchCore Architecture")
![PatchCore Architecture](../../../../../docs/source/images/patchcore/architecture.jpg "PatchCore Architecture")

## Usage

Expand Down Expand Up @@ -47,8 +47,8 @@ All results gathered with seed `42`.

### Sample Results

![Sample Result 1](../../../../docs/source/images/patchcore/results/0.png "Sample Result 1")
![Sample Result 1](../../../../../docs/source/images/patchcore/results/0.png "Sample Result 1")

![Sample Result 2](../../../../docs/source/images/patchcore/results/1.png "Sample Result 2")
![Sample Result 2](../../../../../docs/source/images/patchcore/results/1.png "Sample Result 2")

![Sample Result 3](../../../../docs/source/images/patchcore/results/2.png "Sample Result 3")
![Sample Result 3](../../../../../docs/source/images/patchcore/results/2.png "Sample Result 3")
8 changes: 4 additions & 4 deletions src/anomalib/models/image/reverse_distillation/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,7 @@ During testing, a similar step is followed but this time the cosine distance bet

## Architecture

![Anomaly Detection via Reverse Distillation from One-Class Embedding Architecture](https://raw.githubusercontent.com/openvinotoolkit/anomalib/main/docs/source/images/reverse_distillation/architecture.png "Reverse Distillation Architecture")
![Anomaly Detection via Reverse Distillation from One-Class Embedding Architecture](../../../../../docs/source/images/reverse_distillation/architecture.png "Reverse Distillation Architecture")

## Usage

Expand Down Expand Up @@ -44,8 +44,8 @@ All results gathered with seed `42`, train batch size `16`.

### Sample Results

![Sample Result 1](https://raw.githubusercontent.com/openvinotoolkit/anomalib/main/docs/source/images/reverse_distillation/results/0.png "Sample Result 1")
![Sample Result 1](../../../../../docs/source/images/reverse_distillation/results/0.png "Sample Result 1")

![Sample Result 2](https://raw.githubusercontent.com/openvinotoolkit/anomalib/main/docs/source/images/reverse_distillation/results/1.png "Sample Result 2")
![Sample Result 2](../../../../../docs/source/images/reverse_distillation/results/1.png "Sample Result 2")

![Sample Result 3](https://raw.githubusercontent.com/openvinotoolkit/anomalib/main/docs/source/images/reverse_distillation/results/2.png "Sample Result 3")
![Sample Result 3](../../../../../docs/source/images/reverse_distillation/results/2.png "Sample Result 3")
8 changes: 4 additions & 4 deletions src/anomalib/models/image/stfpm/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,7 @@ During inference, the feature pyramids of teacher and student networks are compa

## Architecture

![STFPM Architecture](https://raw.githubusercontent.com/openvinotoolkit/anomalib/main/docs/source/images/stfpm/architecture.jpg "STFPM Architecture")
![STFPM Architecture](../../../../../docs/source/images/stfpm/architecture.jpg "STFPM Architecture")

## Usage

Expand Down Expand Up @@ -47,8 +47,8 @@ All results gathered with seed `42`.

### Sample Results

![Sample Result 1](../../../../docs/source/images/stfpm/results/0.png "Sample Result 1")
![Sample Result 1](../../../../../docs/source/images/stfpm/results/0.png "Sample Result 1")

![Sample Result 2](../../../../docs/source/images/stfpm/results/1.png "Sample Result 2")
![Sample Result 2](../../../../../docs/source/images/stfpm/results/1.png "Sample Result 2")

![Sample Result 3](../../../../docs/source/images/stfpm/results/2.png "Sample Result 3")
![Sample Result 3](../../../../../docs/source/images/stfpm/results/2.png "Sample Result 3")
20 changes: 10 additions & 10 deletions src/anomalib/models/image/uflow/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@

This is the implementation of the [U-Flow](https://www.researchsquare.com/article/rs-3367286/latest) paper, based on the [original code](https://www.github.com/mtailanian/uflow)

![U-Flow Architecture](https://raw.githubusercontent.com/openvinotoolkit/anomalib/main/docs/source/images/uflow/diagram.png "U-Flow Architecture")
![U-Flow Architecture](../../../../../docs/source/images/uflow/diagram.png "U-Flow Architecture")

## Abstract

Expand All @@ -14,29 +14,29 @@ This multiple-hypothesis testing strategy permits the derivation of robust autom
The segmentation results are evaluated using the Intersection over Union (IoU) metric, and for assessing the generated anomaly maps we report the area under the Receiver Operating Characteristic curve (AUROC), and the area under the per-region-overlap curve (AUPRO).
Extensive experimentation in various datasets shows that the proposed approach produces state-of-the-art results for all metrics and all datasets, ranking first in most MvTec-AD categories, with a mean pixel-level AUROC of 98.74%._

![Teaser image](https://raw.githubusercontent.com/openvinotoolkit/anomalib/main/docs/source/images/uflow/teaser.png)
![Teaser image](../../../../../docs/source/images/uflow/teaser.jpg)

## Localization results

### Pixel AUROC over MVTec-AD Dataset

![Pixel-AUROC results](https://raw.githubusercontent.com/openvinotoolkit/anomalib/main/docs/source/images/uflow/pixel-auroc.png "Pixel-AUROC results")
![Pixel-AUROC results](../../../../../docs/source/images/uflow/pixel-auroc.png "Pixel-AUROC results")

### Pixel AUPRO over MVTec-AD Dataset

![Pixel-AUPRO results](https://raw.githubusercontent.com/openvinotoolkit/anomalib/main/docs/source/images/uflow/pixel-aupro.png "Pixel-AUPRO results")
![Pixel-AUPRO results](../../../../../docs/source/images/uflow/pixel-aupro.png "Pixel-AUPRO results")

## Segmentation results (IoU) with threshold log(NFA)=0

This paper also proposes a method to automatically compute the threshold using the a contrario framework. All results below are obtained with the threshold log(NFA)=0.
In the default code here, for the sake of comparison with all the other methods of the library, the segmentation is done computing the threshold over the anomaly map at train time.
Nevertheless, the code for computing the segmentation mask with the NFA criterion is included in the `src/anomalib/models/uflow/anomaly_map.py`.

![IoU results](https://raw.githubusercontent.com/openvinotoolkit/anomalib/main/docs/source/images/uflow/iou.png "IoU results")
![IoU results](../../../../../docs/source/images/uflow/iou.png "IoU results")

## Results over other datasets

![Results over other datasets](https://raw.githubusercontent.com/openvinotoolkit/anomalib/main/docs/source/images/uflow/more-results.png "Results over other datasets")
![Results over other datasets](../../../../../docs/source/images/uflow/more-results.png "Results over other datasets")

## Benchmarking

Expand Down Expand Up @@ -111,18 +111,18 @@ Normalizing Flow outputs

#### MVTec

![MVTec results - anomalies](https://raw.githubusercontent.com/openvinotoolkit/anomalib/main/docs/source/images/uflow/results-mvtec-anomalies.jpg "MVTec results - anomalies")
![MVTec results - anomalies](../../../../../docs/source/images/uflow/results-mvtec-anomalies.jpg "MVTec results - anomalies")

#### BeanTech, LGG MRI, STC

![BeanTech, LGG MRI, STC results - anomalies](https://raw.githubusercontent.com/openvinotoolkit/anomalib/main/docs/source/images/uflow/results-others-anomalies.jpg "BeanTech, LGG MRI, STC results - anomalies")
![BeanTech, LGG MRI, STC results - anomalies](../../../../../docs/source/images/uflow/results-others-anomalies.jpg "BeanTech, LGG MRI, STC results - anomalies")

### Normal images

#### MVTec

![MVTec results - normal](https://raw.githubusercontent.com/openvinotoolkit/anomalib/main/docs/source/images/uflow/results-mvtec-good.jpg "MVTec results - normal")
![MVTec results - normal](../../../../../docs/source/images/uflow/results-mvtec-good.jpg "MVTec results - normal")

#### BeanTech, LGG MRI, STC

![BeanTech, LGG MRI, STC results - normal](https://raw.githubusercontent.com/openvinotoolkit/anomalib/main/docs/source/images/uflow/results-others-good.jpg "BeanTech, LGG MRI, STC results - normal")
![BeanTech, LGG MRI, STC results - normal](../../../../../docs/source/images/uflow/results-others-good.jpg "BeanTech, LGG MRI, STC results - normal")

0 comments on commit fa5ac1a

Please sign in to comment.