Update model README.md files (open-edge-platform#2076)

Update the README for each algo

Author: samet-akcay

src/anomalib/models/image/cfa/README.md

@@ -16,7 +16,7 @@ Coupled-hypersphere-based Feature Adaptation (CFA) localizes anomalies using fea
 
 ## Usage
 
-`python tools/train.py --model cfa`
+`anomalib train --model Cfa --data MVTec --data.category <category>`
 
 ## Benchmark
 

src/anomalib/models/image/cflow/README.md

@@ -14,7 +14,7 @@ CFLOW model is based on a conditional normalizing flow framework adopted for ano
 
 ## Usage
 
-`python tools/train.py --model cflow`
+`anomalib train --model Cflow --data MVTec --data.category <category>`
 
 ## Benchmark
 

src/anomalib/models/image/csflow/README.md

@@ -31,7 +31,7 @@ The anomaly score for each local position $(i,j)$ of the feature map $y^s$ at sc
 
 ## Usage
 
-`python tools/train.py --model cs_flow`
+`anomalib train --model Csflow --data MVTec --data.category <category>`
 
 ## Benchmark
 

src/anomalib/models/image/dfkde/README.md

@@ -16,7 +16,7 @@ In the anomaly classification stage, the features are first reduced to the first
 
 ## Usage
 
-`python tools/train.py --model dfkde`
+`anomalib train --model Dfkde --data MVTec --data.category <category>`
 
 ## Benchmark
 

src/anomalib/models/image/dfm/README.md

@@ -18,7 +18,7 @@ In the anomaly classification stage, class-conditional PCA transformations and G
 
 ## Usage
 
-`python tools/train.py --model dfm`
+`anomalib train --model Dfm --data MVTec --data.category <category>`
 
 ## Benchmark
 

src/anomalib/models/image/draem/README.md

@@ -16,7 +16,7 @@ For optimal results, DRAEM requires specifying the path to a folder of image dat
 
 ## Usage
 
-`python tools/train.py --model draem`
+`anomalib train --model Draem --data MVTec --data.category <category>`
 
 ## Benchmark
 

src/anomalib/models/image/dsr/README.md

@@ -14,7 +14,7 @@ DSR is a quantized-feature based algorithm that consists of an autoencoder with
 
 ## Usage
 
-`python tools/train.py --model dsr`
+`anomalib train --model Dsr --data MVTec --data.category <category>`
 
 ## Benchmark
 

src/anomalib/models/image/efficient_ad/README.md

@@ -18,7 +18,7 @@ Anomalies are detected as the difference in output feature maps between the teac
 
 ## Usage
 
-`anomalib train --model EfficientAd --data anomalib.data.MVTec --data.train_batch_size 1`
+`anomalib train --model EfficientAd --data anomalib.data.MVTec --data.category <category> --data.train_batch_size 1`
 
 ## Benchmark
 

src/anomalib/models/image/fastflow/README.md

@@ -14,7 +14,7 @@ FastFlow is a two-dimensional normalizing flow-based probability distribution es
 
 ## Usage
 
-`python tools/train.py --model fastflow`
+`anomalib train --model Fastflow --data MVTec --data.category <category>`
 
 ## Benchmark
 

src/anomalib/models/image/ganomaly/README.md

@@ -16,7 +16,7 @@ The key idea here is that, during inference, when an anomalous image is passed t
 
 ## Usage
 
-`python tools/train.py --model ganomaly`
+`anomalib train --model Ganomaly --data MVTec --data.category <category>`
 
 ## Benchmark
 

src/anomalib/models/image/padim/README.md

@@ -16,7 +16,7 @@ During inference, Mahalanobis distance is used to score each patch position of t
 
 ## Usage
 
-`python tools/train.py --model padim`
+`anomalib train --model Padim --data MVTec --data.category <category>`
 
 ## Benchmark
 

src/anomalib/models/image/patchcore/README.md

@@ -16,7 +16,7 @@ During inference this memory bank is coreset subsampled. Coreset subsampling gen
 
 ## Usage
 
-`python tools/train.py --model patchcore`
+`anomalib train --model Patchcore --data MVTec --data.category <category>`
 
 ## Benchmark
 

src/anomalib/models/image/reverse_distillation/README.md

@@ -16,7 +16,7 @@ During testing, a similar step is followed but this time the cosine distance bet
 
 ## Usage
 
-`python tools/train.py --model reverse_distillation`
+`anomalib train --model ReverseDistillation --data MVTec --data.category <category>`
 
 ## Benchmark
 

src/anomalib/models/image/rkde/README.md

@@ -27,7 +27,7 @@ Before fitting the KDE model, the dimensionality of the feature vectors is reduc
 
 ## Usage and parameters
 
-`python tools/train.py --model rkde`
+`anomalib train --model Rkde --data MVTec --data.category <category>`
 
 | Parameter                | Affects Stage      | Description                                                                                                                                                                                                | Type   | Options       |
 | :----------------------- | :----------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :----- | :------------ |

src/anomalib/models/image/stfpm/README.md

@@ -16,7 +16,7 @@ During inference, the feature pyramids of teacher and student networks are compa
 
 ## Usage
 
-`python tools/train.py --model stfpm`
+`anomalib train --model Stfpm --data MVTec --data.category <category>`
 
 ## Benchmark
 

src/anomalib/models/image/uflow/README.md

@@ -52,7 +52,7 @@ In order to obtain the same exact results, although the architecture parameters
 
 ## Usage
 
-`python tools/train.py --model uflow`
+`anomalib train --model Uflow --data MVTec --data.category <category>`
 
 ## Download data