add compare resnet model

app.py

@@ -18,6 +18,7 @@ import glob
 from inference_sam import segmentation_sam
 from explanations import explain
 from inference_resnet import get_triplet_model
+from inference_resnet_v2 import get_resnet_model,inference_resnet_embedding_v2,inference_resnet_finer_v2
 from inference_beit import get_triplet_model_beit
 import pathlib
 import tensorflow as tf
@@ -122,11 +123,7 @@ def get_model(model_name):
         model.load_weights('model_classification/fossil-new.h5')
     elif model_name == 'Fossils':
         n_classes = 142
-        model = get_triplet_model_beit(input_shape = (384, 384, 3),
-                                  embedding_units = 256,
-                                  embedding_depth = 2,
-                                  n_classes = n_classes)
-        model.load_weights('model_classification/fossil-model.h5')
+        model,_,_ = get_resnet_model('model_classification/fossil-model.h5')
     else:
         raise ValueError(f"Model name '{model_name}' is not recognized") 
     return model,n_classes
@@ -161,7 +158,7 @@ def classify_image(input_image, model_name):
     elif 'Fossils' ==model_name:
         from inference_beit import inference_resnet_finer_beit
         model,n_classes = get_model(model_name)
-        result = inference_resnet_finer_beit(input_image,model,size=384,n_classes=n_classes)
+        result = inference_resnet_finer_v2(input_image,model,size=384,n_classes=n_classes)
         return result
     return None
 
@@ -189,7 +186,7 @@ def get_embeddings(input_image,model_name):
     elif 'Fossils' ==model_name:
         from inference_beit import inference_resnet_embedding_beit
         model,n_classes = get_model(model_name)
-        result = inference_resnet_embedding_beit(input_image,model,size=384,n_classes=n_classes)
+        result = inference_resnet_embedding_v2(input_image,model,size=384,n_classes=n_classes)
         return result
     return None
     

inference_resnet_v2.py

@@ -10,10 +10,8 @@ tf.config.set_visible_devices([], 'GPU')
 from keras.applications import resnet
 import tensorflow as tf
 import keras
-import tensorflow.keras.layers as L
 import os
 
-from tensorflow.keras.layers import Dense, GlobalAveragePooling2D
 import matplotlib.pyplot as plt
 from typing import Tuple
 from huggingface_hub import snapshot_download
@@ -51,7 +49,7 @@ def parse_results(top_n,logits):
         results[label] = float(logits[n])
     return results 
 
-def inference_resnet_embedding(x,model,size=384,n_classes=140,n_top=10):
+def inference_resnet_embedding_v2(x,model,size=384,n_classes=140,n_top=10):
         
         
     x = tf.image.resize(x, (size, size))
@@ -61,7 +59,7 @@ def inference_resnet_embedding(x,model,size=384,n_classes=140,n_top=10):
     
     return embedding 
 
-def inference_resnet_finer(x,model,size=384,n_classes=142,n_top=10):
+def inference_resnet_finer_v2(x,model,size=384,n_classes=142,n_top=10):
     
     x = tf.image.resize(x, (size, size))
     x = tf.reshape(x, (-1, 384, 384, 3))/255