From 5c046bea96f560865aac0150c67ebde6b3aabfce Mon Sep 17 00:00:00 2001
From: AlexeyAB <alexeyab84@gmail.com>
Date: Wed, 18 Nov 2020 04:06:28 +0300
Subject: [PATCH] minor fix

---
 build/darknet/x64/cfg/yolov4x-mish.cfg |    1 +
 cfg/yolov4x-mish.cfg                   | 1428 ++++++++++++++++++++++++
 src/yolo_layer.c                       |    2 +-
 3 files changed, 1430 insertions(+), 1 deletion(-)
 create mode 100644 cfg/yolov4x-mish.cfg

diff --git a/build/darknet/x64/cfg/yolov4x-mish.cfg b/build/darknet/x64/cfg/yolov4x-mish.cfg
index 89f2564c..86840e46 100644
--- a/build/darknet/x64/cfg/yolov4x-mish.cfg
+++ b/build/darknet/x64/cfg/yolov4x-mish.cfg
@@ -1131,6 +1131,7 @@ size=1
 stride=1
 pad=1
 activation=mish
+stopbackward=800
 
 ##########################
 
diff --git a/cfg/yolov4x-mish.cfg b/cfg/yolov4x-mish.cfg
new file mode 100644
index 00000000..86840e46
--- /dev/null
+++ b/cfg/yolov4x-mish.cfg
@@ -0,0 +1,1428 @@
+[net]
+# Testing
+#batch=1
+#subdivisions=1
+# Training
+batch=64
+subdivisions=8
+width=672
+height=672
+channels=3
+momentum=0.949
+decay=0.0005
+angle=0
+saturation = 1.5
+exposure = 1.5
+hue=.1
+
+learning_rate=0.00261
+burn_in=1000
+max_batches = 500500
+policy=steps
+steps=400000,450000
+scales=.1,.1
+
+mosaic=1
+
+letter_box=1
+
+[convolutional]
+batch_normalize=1
+filters=32
+size=3
+stride=1
+pad=1
+activation=mish
+
+# Downsample
+
+[convolutional]
+batch_normalize=1
+filters=80
+size=3
+stride=2
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=40
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=80
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+# Downsample
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=3
+stride=2
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=80
+size=1
+stride=1
+pad=1
+activation=mish
+
+[route]
+layers = -2
+
+[convolutional]
+batch_normalize=1
+filters=80
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=80
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=80
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=80
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=80
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=80
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=80
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=80
+size=1
+stride=1
+pad=1
+activation=mish
+
+[route]
+layers = -1,-13
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=1
+stride=1
+pad=1
+activation=mish
+
+# Downsample
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=3
+stride=2
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=1
+stride=1
+pad=1
+activation=mish
+
+[route]
+layers = -2
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=1
+stride=1
+pad=1
+activation=mish
+
+[route]
+layers = -1,-34
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+# Downsample
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=3
+stride=2
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[route]
+layers = -2
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[route]
+layers = -1,-34
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=1
+stride=1
+pad=1
+activation=mish
+
+# Downsample
+
+[convolutional]
+batch_normalize=1
+filters=1280
+size=3
+stride=2
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=1
+stride=1
+pad=1
+activation=mish
+
+[route]
+layers = -2
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=1
+stride=1
+pad=1
+activation=mish
+
+[route]
+layers = -1,-19
+
+[convolutional]
+batch_normalize=1
+filters=1280
+size=1
+stride=1
+pad=1
+activation=mish
+
+########################## 6 0 6 6 3
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=1
+stride=1
+pad=1
+activation=mish
+
+[route]
+layers = -2
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=640
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=1
+stride=1
+pad=1
+activation=mish
+
+### SPP ###
+[maxpool]
+stride=1
+size=5
+
+[route]
+layers=-2
+
+[maxpool]
+stride=1
+size=9
+
+[route]
+layers=-4
+
+[maxpool]
+stride=1
+size=13
+
+[route]
+layers=-1,-3,-5,-6
+### End SPP ###
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=640
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=640
+activation=mish
+
+[route]
+layers = -1, -15
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[upsample]
+stride=2
+
+[route]
+layers = 94
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[route]
+layers = -1, -3
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[route]
+layers = -2
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=320
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=320
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=320
+activation=mish
+
+[route]
+layers = -1, -8
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=1
+stride=1
+pad=1
+activation=mish
+
+[upsample]
+stride=2
+
+[route]
+layers = 57
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=1
+stride=1
+pad=1
+activation=mish
+
+[route]
+layers = -1, -3
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=1
+stride=1
+pad=1
+activation=mish
+
+[route]
+layers = -2
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=160
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=160
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=160
+activation=mish
+
+[route]
+layers = -1, -8
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=1
+stride=1
+pad=1
+activation=mish
+stopbackward=800
+
+##########################
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=320
+activation=mish
+
+[convolutional]
+size=1
+stride=1
+pad=1
+filters=255
+activation=linear
+
+
+[yolo]
+mask = 0,1,2
+anchors = 12, 16, 19, 36, 40, 28, 36, 75, 76, 55, 72, 146, 142, 110, 192, 243, 459, 401
+classes=80
+num=9
+jitter=.1
+objectness_smooth=0
+ignore_thresh = .7
+truth_thresh = 1
+#random=1
+resize=1.5
+iou_thresh=0.2
+iou_normalizer=0.05
+cls_normalizer=0.5
+obj_normalizer=4.0
+iou_loss=ciou
+nms_kind=diounms
+beta_nms=0.6
+new_coords=1
+
+[route]
+layers = -4
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=2
+pad=1
+filters=320
+activation=mish
+
+[route]
+layers = -1, -22
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[route]
+layers = -2
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=320
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=320
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=320
+activation=mish
+
+[route]
+layers = -1,-8
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=640
+activation=mish
+
+[convolutional]
+size=1
+stride=1
+pad=1
+filters=255
+activation=linear
+
+
+[yolo]
+mask = 3,4,5
+anchors = 12, 16, 19, 36, 40, 28, 36, 75, 76, 55, 72, 146, 142, 110, 192, 243, 459, 401
+classes=80
+num=9
+jitter=.1
+objectness_smooth=1
+ignore_thresh = .7
+truth_thresh = 1
+#random=1
+resize=1.5
+iou_thresh=0.2
+iou_normalizer=0.05
+cls_normalizer=0.5
+obj_normalizer=1.0
+iou_loss=ciou
+nms_kind=diounms
+beta_nms=0.6
+new_coords=1
+
+[route]
+layers = -4
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=2
+pad=1
+filters=640
+activation=mish
+
+[route]
+layers = -1, -55
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=1
+stride=1
+pad=1
+activation=mish
+
+[route]
+layers = -2
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=640
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=640
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=640
+activation=mish
+
+[route]
+layers = -1,-8
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=1280
+activation=mish
+
+[convolutional]
+size=1
+stride=1
+pad=1
+filters=255
+activation=linear
+
+
+[yolo]
+mask = 6,7,8
+anchors = 12, 16, 19, 36, 40, 28, 36, 75, 76, 55, 72, 146, 142, 110, 192, 243, 459, 401
+classes=80
+num=9
+jitter=.1
+objectness_smooth=1
+ignore_thresh = .7
+truth_thresh = 1
+#random=1
+resize=1.5
+iou_thresh=0.2
+iou_normalizer=0.05
+cls_normalizer=0.5
+obj_normalizer=0.4
+iou_loss=ciou
+nms_kind=diounms
+beta_nms=0.6
+new_coords=1
diff --git a/src/yolo_layer.c b/src/yolo_layer.c
index 8693342a..f49267c4 100644
--- a/src/yolo_layer.c
+++ b/src/yolo_layer.c
@@ -947,7 +947,7 @@ void forward_yolo_layer_gpu(const layer l, network_state state)
             // if(y->1) x -> inf
             // if(y->0) x -> -inf
             if (l.new_coords) {
-                activate_array_ongpu(l.output_gpu + index, 4 * l.w*l.h, LOGISTIC);    // x,y
+                activate_array_ongpu(l.output_gpu + index, 4 * l.w*l.h, LOGISTIC);    // x,y,w,h
             }
             else {
                 activate_array_ongpu(l.output_gpu + index, 2 * l.w*l.h, LOGISTIC);    // x,y