played around with CASIA-WEB-FACE

DataAnalyser.py

@@ -0,0 +1,50 @@
+
+#from Data import *
+from datasets.Casia import *
+
+'''
+Because the size of samples per class had the biggest impact
+on training outcome, I decided to check the maximum amount of data 
+I can get from a class. 
+The highest I can get is 
+Rank     | Identity ID  |Count 
+-----------------------------------
+1        | 3782         | 35          
+2        | 2820         | 35          
+3        | 3227         | 35          
+4        | 3745         | 34          
+5        | 3699         | 34          
+6        | 8968         | 32          
+7        | 9152         | 32          
+8        | 9256         | 32          
+9        | 2114         | 31          
+...      | ...          | ...            
+17       | 4126         | 31          
+18       | 3185         | 30                  
+...      | ...          | ...       
+50       | 3186         | 30   
+
+as can be seen, 3 classes have 35, 2 have 34, 3 have 32 and the rest have 30.
+'''
+def print_top_identity_stats(dataset, top_n=50):
+    # we get data
+    ids, counts = get_ids_and_counts(dataset)
+    # sort in descending order
+    sorted_counts, sorted_indices = torch.sort(counts, descending=True)
+
+    # coresponding sorted ids
+    sorted_ids = ids[sorted_indices]
+
+    # 4. Slice the first 'top_n' and print
+    print(f"{'Rank':<8} | {'Identity ID':<12} | {'Image Count':<12}")
+    print("-" * 35)
+    
+    for i in range(top_n):
+        identity_id = sorted_ids[i].item()
+        count = sorted_counts[i].item()
+        print(f"{i+1:<8} | {identity_id:<12} | {count:<12}")
+
+# Usage:
+dataset = get_set()
+print_top_identity_stats(dataset, 50)
+