fix: efficientnet and vit working now

requirements.txt

@@ -5,4 +5,5 @@ matplotlib~=3.5.2
 opencv-python~=4.5.5.64
 tqdm~=4.64.0
 tensorflow-addons~=0.17.0
+tensorflow_hub~=0.12.0
 scipy~=1.8.1

src/alexnet.py

@@ -49,11 +49,11 @@ history = siamese.fit(ds, class_weight={0: 1 / NUM_CLASSES, 1: (NUM_CLASSES - 1)
 
 # Build full inference model (from image to image vector):
 inference_model = siamese.get_inference_model(embedding_model)
-inference_model.save(get_modeldir(model_name + '_inference.tf'), save_format='tf', include_optimizer=False)
+inference_model.save(get_modeldir(model_name + '_inference.tf'))
 
 # inference_model = tf.keras.models.load_model(get_modeldir(model_name + '_inference.tf'), compile=False)
 
 print('visualization')
 # compute vectors of the images and their labels, store them in a tsv file for visualization
 projection_vectors = siamese.get_projection_model().predict(emb_vectors)
-project_embeddings(projection_vectors, emb_labels, model_name + '_siamese2')
+project_embeddings(projection_vectors, emb_labels, model_name + '_siamese')

src/alexnet_cifar10.py

@@ -49,7 +49,7 @@ history = siamese.fit(ds, class_weight={0: 1 / NUM_CLASSES, 1: (NUM_CLASSES - 1)
 
 # Build full inference model (from image to image vector):
 inference_model = siamese.get_inference_model(embedding_model)
-inference_model.save(get_modeldir(model_name + '_inference.tf'), save_format='tf', include_optimizer=False)\
+inference_model.save(get_modeldir(model_name + '_inference.tf'))
 
 # inference_model = tf.keras.models.load_model(get_modeldir(model_name + '_inference.tf'), compile=False)
 

src/efficientnet.py

@@ -32,7 +32,7 @@ history = siamese.fit(ds, class_weight={0: 1 / NUM_CLASSES, 1: (NUM_CLASSES - 1)
 
 # Build full inference model (from image to image vector):
 inference_model = siamese.get_inference_model(model)
-inference_model.save(get_modeldir(model_name + '_inference.tf'), save_format='tf', include_optimizer=False)
+inference_model.save(get_modeldir(model_name + '_inference.tf'))
 
 # inference_model = tf.keras.models.load_model(get_modeldir(model_name + '_inference.tf'), compile=False)
 

src/mobilenet.py

@@ -50,7 +50,7 @@ history = siamese.fit(ds, class_weight={0: 1 / NUM_CLASSES, 1: (NUM_CLASSES - 1)
 
 # Build full inference model (from image to image vector):
 inference_model = siamese.get_inference_model(embedding_model)
-inference_model.save(get_modeldir(model_name + '_inference.tf'), save_format='tf', include_optimizer=False)
+inference_model.save(get_modeldir(model_name + '_inference.tf'))
 
 # inference_model = tf.keras.models.load_model(get_modeldir(model_name + '_inference.tf'), compile=False)
 

src/mobilenet_cifar10.py

@@ -49,7 +49,7 @@ history = siamese.fit(ds, class_weight={0: 1 / NUM_CLASSES, 1: (NUM_CLASSES - 1)
 
 # Build full inference model (from image to image vector):
 inference_model = siamese.get_inference_model(embedding_model)
-inference_model.save(get_modeldir(model_name + '_inference.tf'), save_format='tf', include_optimizer=False)
+inference_model.save(get_modeldir(model_name + '_inference.tf'))
 
 # inference_model = tf.keras.models.load_model(get_modeldir(model_name + '_inference.tf'), compile=False)
 

src/model/efficientnet.py

@@ -14,7 +14,7 @@ class EfficientNetModel(Sequential):
         super(EfficientNetModel, self).__init__([
             hub.KerasLayer(MODEL_URL, trainable=False)  # EfficientNet V2 S backbone, frozen weights
         ])
-        self.build(TARGET_SHAPE + (3,))
+        self.build((None,) + TARGET_SHAPE + (3,))
 
     def compile(self, metrics=['accuracy'], **kwargs):
         super().compile(metrics=metrics, **kwargs)

src/model/vit.py

@@ -14,7 +14,7 @@ class VitModel(Sequential):
         super(VitModel, self).__init__([
             hub.KerasLayer(MODEL_URL, trainable=False)  # EfficientNet V2 S backbone, frozen weights
         ])
-        self.build(TARGET_SHAPE + (3,))
+        self.build((None,) + TARGET_SHAPE + (3,))
 
     def compile(self, metrics=['accuracy'], **kwargs):
         super().compile(metrics=metrics, **kwargs)

src/simple.py

@@ -54,7 +54,7 @@ history = siamese.fit(ds, class_weight={0: 1 / NUM_CLASSES, 1: (NUM_CLASSES - 1)
 
 # Build full inference model (from image to image vector):
 inference_model = siamese.get_inference_model(embedding_model)
-inference_model.save(get_modeldir(model_name + '_inference.tf'), save_format='tf', include_optimizer=False)
+inference_model.save(get_modeldir(model_name + '_inference.tf'))
 
 # inference_model = tf.keras.models.load_model(get_modeldir(model_name + '_inference.tf'), compile=False)
 

src/vgg16.py

@@ -50,7 +50,7 @@ history = siamese.fit(ds, class_weight={0: 1 / NUM_CLASSES, 1: (NUM_CLASSES - 1)
 
 # Build full inference model (from image to image vector):
 inference_model = siamese.get_inference_model(embedding_model)
-inference_model.save(get_modeldir(model_name + '_inference.tf'), save_format='tf', include_optimizer=False)
+inference_model.save(get_modeldir(model_name + '_inference.tf'))
 
 # inference_model = tf.keras.models.load_model(get_modeldir(model_name + '_inference.tf'), compile=False)
 

src/vgg16_cifar10.py

@@ -52,7 +52,7 @@ history = siamese.fit(ds, class_weight={0: 1 / NUM_CLASSES, 1: (NUM_CLASSES - 1)
 
 # Build full inference model (from image to image vector):
 inference_model = siamese.get_inference_model(embedding_model)
-inference_model.save(get_modeldir(model_name + '_inference.tf'), save_format='tf', include_optimizer=False)
+inference_model.save(get_modeldir(model_name + '_inference.tf'))
 
 # inference_model = tf.keras.models.load_model(get_modeldir(model_name + '_inference.tf'), compile=False)
 

src/vgg16_small.py

@@ -52,7 +52,7 @@ history = siamese.fit(ds, class_weight={0: 1 / NUM_CLASSES, 1: (NUM_CLASSES - 1)
 
 # Build full inference model (from image to image vector):
 inference_model = siamese.get_inference_model(embedding_model)
-inference_model.save(get_modeldir(model_name + '_inference.tf'), save_format='tf', include_optimizer=False)
+inference_model.save(get_modeldir(model_name + '_inference.tf'))
 
 # inference_model = tf.keras.models.load_model(get_modeldir(model_name + '_inference.tf'), compile=False)
 

src/vit.py

@@ -33,7 +33,7 @@ history = siamese.fit(ds, class_weight={0: 1 / NUM_CLASSES, 1: (NUM_CLASSES - 1)
 
 # Build full inference model (from image to image vector):
 inference_model = siamese.get_inference_model(model)
-inference_model.save(get_modeldir(model_name + '_inference.tf'), save_format='tf', include_optimizer=False)
+inference_model.save(get_modeldir(model_name + '_inference.tf'))
 
 # inference_model = tf.keras.models.load_model(get_modeldir(model_name + '_inference.tf'), compile=False)