From 6847e1aa59e22703183e6dae1604b29b1ea184b2 Mon Sep 17 00:00:00 2001
From: Glenn Jocher <glenn.jocher@ultralytics.com>
Date: Wed, 26 May 2021 14:26:52 +0200
Subject: [PATCH] Updated cache v0.2 with `hashlib` (#3350)

* Update cache v0.2 to include parent hash

Possible fix for https://github.com/ultralytics/yolov5/issues/3349

* Update datasets.py
---
 utils/datasets.py | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

diff --git a/utils/datasets.py b/utils/datasets.py
index 36416b14e138..882c7764c4ab 100755
--- a/utils/datasets.py
+++ b/utils/datasets.py
@@ -1,6 +1,7 @@
 # Dataset utils and dataloaders
 
 import glob
+import hashlib
 import logging
 import math
 import os
@@ -36,9 +37,12 @@
         break
 
 
-def get_hash(files):
-    # Returns a single hash value of a list of files
-    return sum(os.path.getsize(f) for f in files if os.path.isfile(f))
+def get_hash(paths):
+    # Returns a single hash value of a list of paths (files or dirs)
+    size = sum(os.path.getsize(p) for p in paths if os.path.exists(p))  # sizes
+    h = hashlib.md5(str(size).encode())  # hash sizes
+    h.update(''.join(paths).encode())  # hash paths
+    return h.hexdigest()  # return hash
 
 
 def exif_size(img):
@@ -383,7 +387,7 @@ def __init__(self, path, img_size=640, batch_size=16, augment=False, hyp=None, r
         cache_path = (p if p.is_file() else Path(self.label_files[0]).parent).with_suffix('.cache')  # cached labels
         if cache_path.is_file():
             cache, exists = torch.load(cache_path), True  # load
-            if cache['hash'] != get_hash(self.label_files + self.img_files) or 'version' not in cache:  # changed
+            if cache['hash'] != get_hash(self.label_files + self.img_files):  # changed
                 cache, exists = self.cache_labels(cache_path, prefix), False  # re-cache
         else:
             cache, exists = self.cache_labels(cache_path, prefix), False  # cache
@@ -501,9 +505,9 @@ def cache_labels(self, path=Path('./labels.cache'), prefix=''):
 
         x['hash'] = get_hash(self.label_files + self.img_files)
         x['results'] = nf, nm, ne, nc, i + 1
-        x['version'] = 0.1  # cache version
+        x['version'] = 0.2  # cache version
         try:
-            torch.save(x, path)  # save for next time
+            torch.save(x, path)  # save cache for next time
             logging.info(f'{prefix}New cache created: {path}')
         except Exception as e:
             logging.info(f'{prefix}WARNING: Cache directory {path.parent} is not writeable: {e}')  # path not writeable