add missing embedding files

.gitignore

@@ -11,3 +11,5 @@ images/
 
 model/
 model_classification/
+dataset/
+*.png

app.py

@@ -111,7 +111,8 @@ with gr.Blocks(theme='sudeepshouche/minimalist') as demo:
                 classify_image_button = gr.Button("Classify Image")
             
             with gr.Column():
-                segmented_image = gr.outputs.Image(label="SAM output",type='numpy')
+                #segmented_image = gr.outputs.Image(label="SAM output",type='numpy')
+                segmented_image=gr.Image(label="Segmented Image", type='numpy')
                 segment_button = gr.Button("Segment Image")
                 #classify_segmented_button = gr.Button("Classify Segmented Image")
                 

closest_sample.py

@@ -2,12 +2,23 @@ from sklearn.decomposition import PCA
 import pickle as pk
 import numpy as np
 import pandas as pd
+import os
+from huggingface_hub import snapshot_download
 
 
 
 pca_fossils = pk.load(open('pca_fossils_170_finer.pkl','rb'))
 pca_leaves = pk.load(open('pca_leaves_170_finer.pkl','rb'))
-embedding_fossils = np.load('embedding_fossils_170_finer.npy')
+
+if not os.path.exists('dataset'):
+  REPO_ID='Serrelab/Fossils'
+  token = os.environ.get('READ_TOKEN')
+  print(f"Read token:{token}")
+  if token is None:
+     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_leaves = np.load('embedding_leaves.npy')
 
 fossils_pd= pd.read_csv('fossils_paths.csv')
@@ -39,4 +50,4 @@ def get_images(embedding):
     paths= [path.replace('/gpfs/data/tserre/irodri15/Fossils/new_data/leavesdb-v1_1/images/Fossil/Florissant_Fossil/512/full/jpg/',
                          '/media/data_cifs/projects/prj_fossils/data/processed_data/leavesdb-v1_1/images/Fossil/Florissant_Fossil/original/full/jpg/') for path in paths]
     print(paths)
-    return paths 
+    return paths