From 37eaffec7d7a8d82d24082392dd5dc95e56881d3 Mon Sep 17 00:00:00 2001
From: Glenn Jocher <glenn.jocher@ultralytics.com>
Date: Sat, 1 May 2021 17:29:51 +0200
Subject: [PATCH] Curl update (#3004)

* Curl update

* Curl update
---
 data/scripts/get_objects365.py | 2 +-
 utils/general.py               | 7 +++++--
 utils/google_utils.py          | 2 +-
 3 files changed, 7 insertions(+), 4 deletions(-)

diff --git a/data/scripts/get_objects365.py b/data/scripts/get_objects365.py
index 307dfe0da599..d77b26d60691 100644
--- a/data/scripts/get_objects365.py
+++ b/data/scripts/get_objects365.py
@@ -22,7 +22,7 @@
 # Download
 url = "https://dorc.ks3-cn-beijing.ksyun.com/data-set/2020Objects365%E6%95%B0%E6%8D%AE%E9%9B%86/train/"
 download([url + 'zhiyuan_objv2_train.tar.gz'], dir=dir)  # annotations json
-download([url + f for f in [f'patch{i}.tar.gz' for i in range(51)]], dir=dir / 'images' / 'train', threads=8)
+download([url + f for f in [f'patch{i}.tar.gz' for i in range(51)]], dir=dir / 'images' / 'train', curl=True, threads=8)
 
 # Labels
 coco = COCO(dir / 'zhiyuan_objv2_train.json')
diff --git a/utils/general.py b/utils/general.py
index 7e50a7333dea..0c5928d8d06f 100755
--- a/utils/general.py
+++ b/utils/general.py
@@ -183,14 +183,17 @@ def check_dataset(dict):
                 raise Exception('Dataset not found.')
 
 
-def download(url, dir='.', unzip=True, threads=1):
+def download(url, dir='.', unzip=True, curl=False, threads=1):
     # Multi-threaded file download and unzip function
     def download_one(url, dir):
         # Download 1 file
         f = dir / Path(url).name  # filename
         if not f.exists():
             print(f'Downloading {url} to {f}...')
-            torch.hub.download_url_to_file(url, f, progress=True)  # download
+            if curl:
+                os.system(f"curl -L '{url}' -o '{f}' --retry 9 -C -")  # curl download, retry and resume on fail
+            else:
+                torch.hub.download_url_to_file(url, f, progress=True)  # torch download
         if unzip and f.suffix in ('.zip', '.gz'):
             print(f'Unzipping {f}...')
             if f.suffix == '.zip':
diff --git a/utils/google_utils.py b/utils/google_utils.py
index 6a4660bad509..eae2d1b9ffcc 100644
--- a/utils/google_utils.py
+++ b/utils/google_utils.py
@@ -47,7 +47,7 @@ def attempt_download(file, repo='ultralytics/yolov5'):
                 assert redundant, 'No secondary mirror'
                 url = f'https://storage.googleapis.com/{repo}/ckpt/{name}'
                 print(f'Downloading {url} to {file}...')
-                os.system(f'curl -L {url} -o {file}')  # torch.hub.download_url_to_file(url, weights)
+                os.system(f"curl -L '{url}' -o '{file}' --retry 3 -C -")  # curl download, retry and resume on fail
             finally:
                 if not file.exists() or file.stat().st_size < 1E6:  # check
                     file.unlink(missing_ok=True)  # remove partial downloads