From 300e2b5dfc04e626f2e9aa8fce5b8b1a4ec678e9 Mon Sep 17 00:00:00 2001
From: Glenn Jocher <glenn.jocher@ultralytics.com>
Date: Mon, 10 Sep 2018 16:41:02 +0200
Subject: [PATCH] updates

---
 test.py        | 2 +-
 utils/gcp.sh   | 8 ++++++++
 utils/utils.py | 2 +-
 3 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/test.py b/test.py
index 5ff81729..7252e291 100644
--- a/test.py
+++ b/test.py
@@ -11,7 +11,7 @@ parser.add_argument('-weights_path', type=str, default='checkpoints/yolov3.weigh
 parser.add_argument('-class_path', type=str, default='data/coco.names', help='path to class label file')
 parser.add_argument('-iou_thres', type=float, default=0.5, help='iou threshold required to qualify as detected')
 parser.add_argument('-conf_thres', type=float, default=0.5, help='object confidence threshold')
-parser.add_argument('-nms_thres', type=float, default=0.45, help='iou threshold for non-maximum suppression')
+parser.add_argument('-nms_thres', type=float, default=0.4, help='iou threshold for non-maximum suppression')
 parser.add_argument('-n_cpu', type=int, default=0, help='number of cpu threads to use during batch generation')
 parser.add_argument('-img_size', type=int, default=416, help='size of each image dimension')
 parser.add_argument('-use_cuda', type=bool, default=True, help='whether to use cuda if available')
diff --git a/utils/gcp.sh b/utils/gcp.sh
index 50e1b9a5..ed1d189c 100644
--- a/utils/gcp.sh
+++ b/utils/gcp.sh
@@ -12,3 +12,11 @@ python3 detect.py
 
 # Test
 python3 test.py -img_size 416 -weights_path checkpoints/yolov3.weights
+
+
+sudo rm -rf yolov3 && git clone https://github.com/ultralytics/yolov3
+cd yolov3
+cd checkpoints
+wget https://pjreddie.com/media/files/yolov3.weights
+cd ..
+python3 test.py -img_size 416 -weights_path checkpoints/yolov3.weights
diff --git a/utils/utils.py b/utils/utils.py
index fc590bc1..fe620193 100755
--- a/utils/utils.py
+++ b/utils/utils.py
@@ -99,7 +99,7 @@ def ap_per_class(tp, conf, pred_cls, target_cls):
     tp, conf, pred_cls = tp[i], conf[i], pred_cls[i]
 
     # Find unique classes
-    unique_classes = target_cls# np.unique(np.concatenate((pred_cls, target_cls), 0))
+    unique_classes = np.unique(np.concatenate((pred_cls, target_cls), 0))
 
     # Create Precision-Recall curve and compute AP for each class
     ap = []