Merge pull request #223 from rizoudal/rizoudal

Refactor: commented out ViT-related mentions in files

README.md

@@ -14,7 +14,7 @@ The open-source software AUCMEDI allows fast setup of medical image classificati
 - Wide range of 2D/3D data entry options with interfaces to the most common medical image formats such as DICOM, MetaImage, NifTI, PNG or TIF already supplied.
 - Selection of pre-processing methods for preparing images, such as augmentation processes, color conversions, windowing, filtering, resizing and normalization.
 - Use of deep neural networks for binary, multi-class as well as multi-label classification and efficient methods against class imbalances using modern loss functions such as focal loss.
-- Library from modern architectures, like ResNet up to EfficientNet and Vision-Transformers (ViT)⁠.
+- Library from modern architectures, like ResNet up to ConvNeXt. <!-- and Vision-Transformers (ViT)⁠.-->
 - Complex ensemble learning techniques (combination of predictions) using test-time augmentation, bagging via cross-validation or stacking via logistic regressions.
 - Explainable AI to explain opaque decision-making processes of the models using activation maps such as Grad-CAM or backpropagation.
 - Automated Machine Learning (AutoML) mentality to ensure easy deployment, integration and maintenance of complex medical image classification pipelines (Docker).

aucmedi/automl/block_train.py

@@ -24,7 +24,6 @@
 import numpy as np
 import json
 from tensorflow.keras.metrics import AUC
-from tensorflow_addons.metrics import F1Score
 from tensorflow.keras.callbacks import ModelCheckpoint, CSVLogger, \
                                        ReduceLROnPlateau, EarlyStopping
 # Internal libraries
@@ -140,8 +139,7 @@ def block_train(config):
                 "workers": config["workers"],
                 "batch_queue_size": 4,
                 "loss": loss,
-                "metrics": [AUC(100), F1Score(num_classes=class_n,
-                                              average="macro")],
+                "metrics": [AUC(100)],
                 "pretrained_weights": True,
                 "multiprocessing": False,
     }

aucmedi/neural_network/architectures/image/__init__.py

@@ -61,10 +61,10 @@
 # Xception
 from aucmedi.neural_network.architectures.image.xception import Xception
 # Vision Transformer (ViT)
-from aucmedi.neural_network.architectures.image.vit_b16 import ViT_B16
-from aucmedi.neural_network.architectures.image.vit_b32 import ViT_B32
-from aucmedi.neural_network.architectures.image.vit_l16 import ViT_L16
-from aucmedi.neural_network.architectures.image.vit_l32 import ViT_L32
+# from aucmedi.neural_network.architectures.image.vit_b16 import ViT_B16
+# from aucmedi.neural_network.architectures.image.vit_b32 import ViT_B32
+# from aucmedi.neural_network.architectures.image.vit_l16 import ViT_L16
+# from aucmedi.neural_network.architectures.image.vit_l32 import ViT_L32
 # ConvNeXt
 from aucmedi.neural_network.architectures.image.convnext_base import ConvNeXtBase
 from aucmedi.neural_network.architectures.image.convnext_tiny import ConvNeXtTiny
@@ -103,10 +103,10 @@
     "VGG16": VGG16,
     "VGG19": VGG19,
     "Xception": Xception,
-    "ViT_B16": ViT_B16,
-    "ViT_B32": ViT_B32,
-    "ViT_L16": ViT_L16,
-    "ViT_L32": ViT_L32,
+    # "ViT_B16": ViT_B16,
+    # "ViT_B32": ViT_B32,
+    # "ViT_L16": ViT_L16,
+    # "ViT_L32": ViT_L32,
     "ConvNeXtBase": ConvNeXtBase,
     "ConvNeXtTiny": ConvNeXtTiny,
     "ConvNeXtSmall": ConvNeXtSmall,
@@ -190,10 +190,10 @@
     "VGG16": "caffe",
     "VGG19": "caffe",
     "Xception": "tf",
-    "ViT_B16": "tf",
-    "ViT_B32": "tf",
-    "ViT_L16": "tf",
-    "ViT_L32": "tf",
+    # "ViT_B16": "tf",
+    # "ViT_B32": "tf",
+    # "ViT_L16": "tf",
+    # "ViT_L32": "tf",
     "ConvNeXtBase": None,
     "ConvNeXtTiny": None,
     "ConvNeXtSmall": None,

requirements.txt

@@ -8,8 +8,7 @@ scikit-image==0.21.0
 lime==0.2.0.1
 pooch==1.6.0
 classification-models-3D==1.0.10
-vit-keras==0.1.2
-tensorflow-addons==0.21.0
+# vit-keras==0.1.2
 Keras-Applications==1.0.8
 SimpleITK==2.2.0
 batchgenerators==0.25

setup.py

@@ -35,8 +35,7 @@
                       'lime>=0.2.0.1',
                       'pooch>=1.6.0',
                       'classification-models-3D>=1.0.10',
-                      'vit-keras>=0.1.2',
-                      'tensorflow-addons>=0.21.0',
+                      # 'vit-keras>=0.1.2',
                       'Keras-Applications==1.0.8',
                       'SimpleITK>=2.2.0',
                       'batchgenerators>=0.25',

tests/test_architectures_image.py

@@ -665,7 +665,7 @@ def test_Xception(self):
     #              Architecture: ViT B16              #
     #-------------------------------------------------#
     # Functionality and Interoperability testing deactived due to too intensive RAM requirements
-    def test_ViT_B16(self):
+    # def test_ViT_B16(self):
         # self.datagen_RGB.sf_resize = Resize(shape=(224, 224))
         # arch = ViT_B16(Classifier(n_labels=4), channels=3,
         #                             input_shape=(224, 224))
@@ -676,16 +676,16 @@ def test_ViT_B16(self):
         #                        batch_queue_size=1, input_shape=(224, 224))
         # try : model.model.summary()
         # except : raise Exception()
-        self.assertTrue(supported_standardize_mode["ViT_B16"] == "tf")
-        self.assertTrue(sdm_global["2D.ViT_B16"] == "tf")
-        self.assertTrue("2D.ViT_B16" in architecture_dict)
+        # self.assertTrue(supported_standardize_mode["ViT_B16"] == "tf")
+        # self.assertTrue(sdm_global["2D.ViT_B16"] == "tf")
+        # self.assertTrue("2D.ViT_B16" in architecture_dict)
         # self.datagen_RGB.sf_resize = Resize(shape=(32, 32))
 
     #-------------------------------------------------#
     #              Architecture: ViT B32              #
     #-------------------------------------------------#
     # Functionality and Interoperability testing deactived due to too intensive RAM requirements
-    def test_ViT_B32(self):
+    # def test_ViT_B32(self):
         # self.datagen_RGB.sf_resize = Resize(shape=(224, 224))
         # arch = ViT_B32(Classifier(n_labels=4), channels=3,
         #                             input_shape=(224, 224))
@@ -696,16 +696,16 @@ def test_ViT_B32(self):
         #                        batch_queue_size=1, input_shape=(224, 224))
         # try : model.model.summary()
         # except : raise Exception()
-        self.assertTrue(supported_standardize_mode["ViT_B32"] == "tf")
-        self.assertTrue(sdm_global["2D.ViT_B32"] == "tf")
-        self.assertTrue("2D.ViT_B32" in architecture_dict)
+        # self.assertTrue(supported_standardize_mode["ViT_B32"] == "tf")
+        # self.assertTrue(sdm_global["2D.ViT_B32"] == "tf")
+        # self.assertTrue("2D.ViT_B32" in architecture_dict)
         # self.datagen_RGB.sf_resize = Resize(shape=(32, 32))
 
     #-------------------------------------------------#
     #              Architecture: ViT L16              #
     #-------------------------------------------------#
     # Functionality and Interoperability testing deactived due to too intensive RAM requirements
-    def test_ViT_L16(self):
+    # def test_ViT_L16(self):
         # self.datagen_RGB.sf_resize = Resize(shape=(384, 384))
         # arch = ViT_L16(Classifier(n_labels=4), channels=3,
         #                             input_shape=(384, 384))
@@ -716,16 +716,16 @@ def test_ViT_L16(self):
         #                        batch_queue_size=1, input_shape=(384, 384))
         # try : model.model.summary()
         # except : raise Exception()
-        self.assertTrue(supported_standardize_mode["ViT_L16"] == "tf")
-        self.assertTrue(sdm_global["2D.ViT_L16"] == "tf")
-        self.assertTrue("2D.ViT_L16" in architecture_dict)
+        # self.assertTrue(supported_standardize_mode["ViT_L16"] == "tf")
+        # self.assertTrue(sdm_global["2D.ViT_L16"] == "tf")
+        # self.assertTrue("2D.ViT_L16" in architecture_dict)
         # self.datagen_RGB.sf_resize = Resize(shape=(32, 32))
 
     #-------------------------------------------------#
     #              Architecture: ViT L32              #
     #-------------------------------------------------#
     # Functionality and Interoperability testing deactived due to too intensive RAM requirements
-    def test_ViT_L32(self):
+    # def test_ViT_L32(self):
         # self.datagen_RGB.sf_resize = Resize(shape=(384, 384))
         # arch = ViT_L32(Classifier(n_labels=4), channels=3,
         #                             input_shape=(384, 384))
@@ -736,9 +736,9 @@ def test_ViT_L32(self):
         #                        batch_queue_size=1, input_shape=(384, 384))
         # try : model.model.summary()
         # except : raise Exception()
-        self.assertTrue(supported_standardize_mode["ViT_L32"] == "tf")
-        self.assertTrue(sdm_global["2D.ViT_L32"] == "tf")
-        self.assertTrue("2D.ViT_L32" in architecture_dict)
+        # self.assertTrue(supported_standardize_mode["ViT_L32"] == "tf")
+        # self.assertTrue(sdm_global["2D.ViT_L32"] == "tf")
+        # self.assertTrue("2D.ViT_L32" in architecture_dict)
         # self.datagen_RGB.sf_resize = Resize(shape=(32, 32))
 
     #-------------------------------------------------#