reference bucket img for closest sample

.gitignore

@@ -13,3 +13,4 @@ model/
 model_classification/
 dataset/
 *.png
+*.jpg

app.py

@@ -100,7 +100,7 @@ def explain_image(input_image,model_name):
     print('done')
     return saliency, integrated, smoothgrad,
     
-
+#minimalist theme
 with gr.Blocks(theme='sudeepshouche/minimalist') as demo:
     
     with gr.Tab(" Florrissant Fossils"):
@@ -120,7 +120,7 @@ with gr.Blocks(theme='sudeepshouche/minimalist') as demo:
                 model_name = gr.Dropdown(
                     ["Mummified 170", "Rock 170"],
                     multiselect=False,
-                    value="Rock 170",
+                    value="Rock 170", # default option
                     label="Model",
                     interactive=True,
                 )
@@ -170,7 +170,7 @@ with gr.Blocks(theme='sudeepshouche/minimalist') as demo:
         find_closest_btn.click(find_closest, inputs=[input_image,model_name], outputs=[closest_image_0,closest_image_1,closest_image_2,closest_image_3,closest_image_4])
         #classify_segmented_button.click(classify_image, inputs=[segmented_image,model_name], outputs=class_predicted)
         
-demo.queue()     
+demo.queue()     # manage multiple incoming requests
    
 if os.getenv('SYSTEM') == 'spaces':
     demo.launch(width='40%',auth=(os.environ.get('USERNAME'), os.environ.get('PASSWORD')))

closest_sample.py

@@ -4,7 +4,7 @@ import numpy as np
 import pandas as pd
 import os
 from huggingface_hub import snapshot_download
-
+import requests
 
 
 pca_fossils = pk.load(open('pca_fossils_170_finer.pkl','rb'))
@@ -24,10 +24,18 @@ embedding_fossils = np.load('dataset/embedding_fossils_170_finer.npy')
 fossils_pd= pd.read_csv('fossils_paths.csv')
 
 def pca_distance(pca,sample,embedding):
+    """
+    Args:
+        pca:fitted PCA model
+        sample:sample for which to find the closest embeddings
+        embedding:embeddings of the dataset
+    Returns:
+        The indices of the five closest embeddings to the sample
+    """
     s = pca.transform(sample.reshape(1,-1))
     all = pca.transform(embedding[:,-1])
     distances = np.linalg.norm(all - s, axis=1)
-    print(distances)
+    #print(distances)
     return np.argsort(distances)[:5]
 
 def return_paths(argsorted,files):
@@ -36,6 +44,16 @@ def return_paths(argsorted,files):
         paths.append(files[i])
     return paths
 
+def download_public_image(url, destination_path):
+    response = requests.get(url)
+    if response.status_code == 200:
+        with open(destination_path, 'wb') as f:
+            f.write(response.content)
+        print(f"Downloaded image to {destination_path}")
+        return True
+    else:
+        print(f"Failed to download image from bucket. Status code: {response.status_code}")
+        return False
 
 def get_images(embedding):
     
@@ -47,7 +65,18 @@ def get_images(embedding):
     
     paths = return_paths(pca_d,fossils_paths)
     print(paths)
-    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
+
+    folder_florissant = 'https://storage.googleapis.com/serrelab/prj_fossils/2024/Florissant_Fossil_v2.0/'
+    folder_general = 'https://storage.googleapis.com/serrelab/prj_fossils/2024/General_Fossil_v2.0/'
+    
+    for i, path in enumerate(paths):
+        local_file_path = f'image_{i}.jpg'
+        public_path_florissant = path.replace('/gpfs/data/tserre/irodri15/Fossils/new_data/leavesdb-v1_1/images/Fossil/Florissant_Fossil/512/full/jpg/', folder_florissant)
+        success = download_public_image(public_path_florissant, local_file_path)
+
+        if not success:
+            public_path_general = path.replace('/gpfs/data/tserre/irodri15/Fossils/new_data/leavesdb-v1_1/images/Fossil/Florissant_Fossil/512/full/jpg/', folder_general)
+            download_public_image(public_path_general, local_file_path)
+    #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]
+    return paths