update closest_sample to use new embeddings

app.py

@@ -110,21 +110,21 @@ def get_model(model_name):
                         backbone_class=tf.keras.applications.ResNet50V2,
                         nb_classes = n_classes,load_weights=False,finer_model=True,backbone_name ='Resnet50v2')
         model.load_weights('model_classification/rock-170.h5')
-    # elif model_name == 'Fossils 142':
+    # elif model_name == 'Fossils 142': #BEiT
     #     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-142.h5')
-    # elif model_name == 'Fossils new':
+    # elif model_name == 'Fossils new': # BEiT-v2
     #     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-new.h5')
-    elif model_name == 'Fossils 142':
+    elif model_name == 'Fossils 142': # new resnet
         n_classes = 142
         model,_,_ = get_resnet_model('model_classification/fossil-model.h5')
     else:

check_arch.py

@@ -1,21 +0,0 @@
-import h5py
-
-def print_model_details(file_path):
-    with h5py.File(file_path, 'r') as f:
-        print(f.keys())  # Print layers
-        print(len(f.keys())) 
-        print("")
-        for key in f.keys():
-            print(len(list(f[key].keys())))
-            print(f"{key}: {list(f[key].keys())}")  # Print details of each layer)
-print('rock')
-print_model_details('model_classification/rock-170.h5')
-print('mummified-170')
-print_model_details('model_classification/mummified-170.h5')
-print('BEiT')
-print_model_details('model_classification/fossil-142.h5')
-print('BEiT New')
-print_model_details('model_classification/fossil-new.h5')
-print("Newest:")
-print_model_details('model_classification/fossil-model.h5')
-

closest_sample.py

@@ -9,8 +9,8 @@ import matplotlib.pyplot as plt
 from collections import Counter
 
 
-pca_fossils = pk.load(open('pca_fossils_170_finer.pkl','rb'))
-pca_leaves = pk.load(open('pca_leaves_170_finer.pkl','rb'))
+pca_fossils = pk.load(open('pca_fossils_142_resnet.pkl','rb'))
+pca_leaves = pk.load(open('pca_leaves_142_resnet.pkl','rb'))
 
 if not os.path.exists('dataset'):
   REPO_ID='Serrelab/Fossils'
@@ -20,7 +20,7 @@ if not os.path.exists('dataset'):
      print("warning! A read token in env variables is needed for authentication.")
   snapshot_download(repo_id=REPO_ID, token=token,repo_type='dataset',local_dir='dataset')
 
-embedding_fossils = np.load('dataset/embedding_fossils_170_finer.npy')
+embedding_fossils = np.load('dataset/embedding_leaves_142_finer.npy')
 #embedding_leaves = np.load('embedding_leaves.npy')
 
 fossils_pd= pd.read_csv('fossils_paths.csv')

test.py

@@ -0,0 +1,29 @@
+# import h5py
+
+# def print_model_details(file_path):
+#     with h5py.File(file_path, 'r') as f:
+#         print(f.keys())  # Print layers
+#         print(len(f.keys())) 
+#         print("")
+#         for key in f.keys():
+#             print(len(list(f[key].keys())))
+#             print(f"{key}: {list(f[key].keys())}")  # Print details of each layer)
+# print('rock')
+# print_model_details('model_classification/rock-170.h5')
+# print('mummified-170')
+# print_model_details('model_classification/mummified-170.h5')
+# print('BEiT')
+# print_model_details('model_classification/fossil-142.h5')
+# print('BEiT New')
+# print_model_details('model_classification/fossil-new.h5')
+# print("Newest:")
+# print_model_details('model_classification/fossil-model.h5')
+
+
+import numpy as np
+
+# Load the .npy file
+embedding = np.load('embedding.npy')
+
+# Check the shape of the array
+print(embedding.shape)