update readme

sadknight2130 · Nov 20, 2020 · 63829e1 · 63829e1
1 parent f6ad011
commit 63829e1
Show file tree

Hide file tree

Showing 2 changed files with 2 additions and 2 deletions.
diff --git a/pytorch_object_detection/yolov3_spp/README.md b/pytorch_object_detection/yolov3_spp/README.md
@@ -110,7 +110,7 @@ cfg_path = "./cfg/yolov3-spp.cfg"
 * ```yolov3-spp-ultralytics-416.pt```: 链接: https://pan.baidu.com/s/1cK3USHKxDx-d5dONij52lA  密码: r3vm
 * ```yolov3-spp-ultralytics-512.pt```: 链接: https://pan.baidu.com/s/1k5yeTZZNv8Xqf0uBXnUK-g  密码: e3k1
 * ```yolov3-spp-ultralytics-608.pt```: 链接: https://pan.baidu.com/s/1GI8BA0wxeWMC0cjrC01G7Q  密码: ma3t
-* ```yolov3spp-voc-512.pth``` **(这是我在视频演示训练中得到的权重)**: 链接: https://pan.baidu.com/s/1fzXPFYvPy95Q9f5IR5Voqg  密码: ct2n
+* ```yolov3spp-voc-512.pt``` **(这是我在视频演示训练中得到的权重)**: 链接: https://pan.baidu.com/s/1JJAElFSVbV1lrcJhQTeoGw  密码: b1e3
 
 
 ## 6 数据集，本例程使用的是PASCAL VOC2012数据集

diff --git a/pytorch_object_detection/yolov3_spp/train.py b/pytorch_object_detection/yolov3_spp/train.py
@@ -266,7 +266,7 @@ def train(hyp):
     parser.add_argument('--savebest', type=bool, default=False, help='only save best checkpoint')
     parser.add_argument('--notest', action='store_true', help='only test final epoch')
     parser.add_argument('--cache-images', action='store_true', help='cache images for faster training')
-    parser.add_argument('--weights', type=str, default='weights/yolov3spp-voc-512.pth',
+    parser.add_argument('--weights', type=str, default='weights/yolov3-spp-ultralytics-512.pt',
                         help='initial weights path')
     parser.add_argument('--name', default='', help='renames results.txt to results_name.txt if supplied')
     parser.add_argument('--device', default='cuda:0', help='device id (i.e. 0 or 0,1 or cpu)')