Update anomaly transforms (#4059)

* Update transforms Signed-off-by: Ashwin Vaidya <[email protected]> * Update transforms Signed-off-by: Ashwin Vaidya <[email protected]> * Update changelog Signed-off-by: Ashwin Vaidya <[email protected]> * Update __init__.py --------- Signed-off-by: Ashwin Vaidya <[email protected]> Co-authored-by: Emily Chun <[email protected]>
openvinotoolkit · Oct 24, 2024 · fbf0f3e · fbf0f3e
1 parent d85f5da
commit fbf0f3e
Show file tree

Hide file tree

Showing 3 changed files with 10 additions and 11 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -68,6 +68,8 @@ All notable changes to this project will be documented in this file.
 
 ### Bug fixes
 
+- Update anomaly base transforms to use square resizing
+  (<https://github.com/openvinotoolkit/training_extensions/pull/4059>)
 - Fix Combined Dataloader & unlabeled warmup loss in Semi-SL
   (<https://github.com/openvinotoolkit/training_extensions/pull/3723>)
 - Revert #3579 to fix issues with replacing coco_instance with a different format in some dataset

diff --git a/src/otx/__init__.py b/src/otx/__init__.py
@@ -3,7 +3,7 @@
 # Copyright (C) 2024 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-__version__ = "2.2.0rc10"
+__version__ = "2.2.0rc11"
 
 import os
 from pathlib import Path

diff --git a/src/otx/recipe/_base_/data/anomaly.yaml b/src/otx/recipe/_base_/data/anomaly.yaml
@@ -1,5 +1,5 @@
 task: ANOMALY_CLASSIFICATION
-input_size: 256
+input_size: [256, 256]
 data_format: mvtec
 mem_cache_size: 1GB
 mem_cache_img_max_size: null
@@ -13,11 +13,10 @@ train_subset:
   batch_size: 32
   num_workers: 4
   transforms:
-    - class_path: otx.core.data.transform_libs.torchvision.ResizetoLongestEdge
+    - class_path: torchvision.transforms.v2.Resize
       init_args:
-        size: $(input_size)
+        size: [256, 256]
         antialias: true
-    - class_path: otx.core.data.transform_libs.torchvision.PadtoSquare
     - class_path: torchvision.transforms.v2.ToDtype
       init_args:
         dtype: ${as_torch_dtype:torch.float32}
@@ -36,11 +35,10 @@ val_subset:
   batch_size: 32
   num_workers: 4
   transforms:
-    - class_path: otx.core.data.transform_libs.torchvision.ResizetoLongestEdge
+    - class_path: torchvision.transforms.v2.Resize
       init_args:
-        size: $(input_size)
+        size: [256, 256]
         antialias: true
-    - class_path: otx.core.data.transform_libs.torchvision.PadtoSquare
     - class_path: torchvision.transforms.v2.ToDtype
       init_args:
         dtype: ${as_torch_dtype:torch.float32}
@@ -59,11 +57,10 @@ test_subset:
   batch_size: 32
   num_workers: 4
   transforms:
-    - class_path: otx.core.data.transform_libs.torchvision.ResizetoLongestEdge
+    - class_path: torchvision.transforms.v2.Resize
       init_args:
-        size: $(input_size)
+        size: [256, 256]
         antialias: true
-    - class_path: otx.core.data.transform_libs.torchvision.PadtoSquare
     - class_path: torchvision.transforms.v2.ToDtype
       init_args:
         dtype: ${as_torch_dtype:torch.float32}