:eyeofthetiger::noseofthetiger::eyeofthetiger2:

cfg/coco.data

@@ -1,7 +1,7 @@
 classes= 80
 train  = /home/pjreddie/data/coco/trainvalno5k.txt
-#valid  = coco_testdev
-valid = data/coco_val_5k.list
+valid  = coco_testdev
+#valid = data/coco_val_5k.list
 names = data/coco.names
 backup = /home/pjreddie/backup/
 eval=coco

cfg/go.cfg

@@ -0,0 +1,135 @@
+[net]
+batch=512
+subdivisions=1
+height=19
+width=19
+channels=1
+momentum=0.9
+decay=0.0005
+
+burn_in=1000
+learning_rate=0.1
+policy=poly
+power=4
+max_batches=10000000
+
+[convolutional]
+filters=256
+size=3
+stride=1
+pad=1
+activation=relu
+batch_normalize=1
+
+[convolutional]
+filters=256
+size=3
+stride=1
+pad=1
+activation=relu
+batch_normalize=1
+
+[convolutional]
+filters=256
+size=3
+stride=1
+pad=1
+activation=relu
+batch_normalize=1
+
+[convolutional]
+filters=256
+size=3
+stride=1
+pad=1
+activation=relu
+batch_normalize=1
+
+[convolutional]
+filters=256
+size=3
+stride=1
+pad=1
+activation=relu
+batch_normalize=1
+
+[convolutional]
+filters=256
+size=3
+stride=1
+pad=1
+activation=relu
+batch_normalize=1
+
+[convolutional]
+filters=256
+size=3
+stride=1
+pad=1
+activation=relu
+batch_normalize=1
+
+[convolutional]
+filters=256
+size=3
+stride=1
+pad=1
+activation=relu
+batch_normalize=1
+
+[convolutional]
+filters=256
+size=3
+stride=1
+pad=1
+activation=relu
+batch_normalize=1
+
+[convolutional]
+filters=256
+size=3
+stride=1
+pad=1
+activation=relu
+batch_normalize=1
+
+[convolutional]
+filters=256
+size=3
+stride=1
+pad=1
+activation=relu
+batch_normalize=1
+
+[convolutional]
+filters=256
+size=3
+stride=1
+pad=1
+activation=relu
+batch_normalize=1
+
+[convolutional]
+filters=256
+size=3
+stride=1
+pad=1
+activation=relu
+batch_normalize=1
+
+[convolutional]
+filters=1
+size=1
+stride=1
+pad=1
+activation=linear
+
+[reorg]
+extra=1
+stride=1
+
+[softmax]
+
+[cost]
+type=sse
+

cfg/go.test.cfg

@@ -7,13 +7,13 @@ channels=1
 momentum=0.9
 decay=0.0005
 
-learning_rate=0.1
+learning_rate=0.01
 policy=poly
 power=4
-max_batches=400000
+max_batches=100000
 
 [convolutional]
-filters=192
+filters=256
 size=3
 stride=1
 pad=1
@@ -21,7 +21,7 @@ activation=relu
 batch_normalize=1
 
 [convolutional]
-filters=192
+filters=256
 size=3
 stride=1
 pad=1
@@ -29,7 +29,7 @@ activation=relu
 batch_normalize=1
 
 [convolutional]
-filters=192
+filters=256
 size=3
 stride=1
 pad=1
@@ -37,7 +37,7 @@ activation=relu
 batch_normalize=1
 
 [convolutional]
-filters=192
+filters=256
 size=3
 stride=1
 pad=1
@@ -45,7 +45,7 @@ activation=relu
 batch_normalize=1
 
 [convolutional]
-filters=192
+filters=256
 size=3
 stride=1
 pad=1
@@ -53,7 +53,7 @@ activation=relu
 batch_normalize=1
 
 [convolutional]
-filters=192
+filters=256
 size=3
 stride=1
 pad=1
@@ -61,7 +61,7 @@ activation=relu
 batch_normalize=1
 
 [convolutional]
-filters=192
+filters=256
 size=3
 stride=1
 pad=1
@@ -69,7 +69,7 @@ activation=relu
 batch_normalize=1
 
 [convolutional]
-filters=192
+filters=256
 size=3
 stride=1
 pad=1
@@ -77,7 +77,7 @@ activation=relu
 batch_normalize=1
 
 [convolutional]
-filters=192
+filters=256
 size=3
 stride=1
 pad=1
@@ -85,7 +85,7 @@ activation=relu
 batch_normalize=1
 
 [convolutional]
-filters=192
+filters=256
 size=3
 stride=1
 pad=1
@@ -93,7 +93,7 @@ activation=relu
 batch_normalize=1
 
 [convolutional]
-filters=192
+filters=256
 size=3
 stride=1
 pad=1
@@ -101,7 +101,7 @@ activation=relu
 batch_normalize=1
 
 [convolutional]
-filters=192
+filters=256
 size=3
 stride=1
 pad=1
@@ -109,14 +109,13 @@ activation=relu
 batch_normalize=1
 
 [convolutional]
-filters=192
+filters=256
 size=3
 stride=1
 pad=1
 activation=relu
 batch_normalize=1
 
-
 [convolutional]
 filters=1
 size=1
@@ -124,6 +123,10 @@ stride=1
 pad=1
 activation=linear
 
+[reorg]
+extra=1
+stride=1
+
 [softmax]
 
 [cost]

cfg/tiny-yolo-voc.cfg

@@ -12,7 +12,7 @@ exposure = 1.5
 hue=.1
 
 learning_rate=0.001
-max_batches = 40100
+max_batches = 40200
 policy=steps
 steps=-1,100,20000,30000
 scales=.1,10,.1,.1

cfg/yolo-voc.2.0.cfg

@@ -0,0 +1,244 @@
+[net]
+batch=64
+subdivisions=8
+height=416
+width=416
+channels=3
+momentum=0.9
+decay=0.0005
+angle=0
+saturation = 1.5
+exposure = 1.5
+hue=.1
+
+learning_rate=0.0001
+max_batches = 45000
+policy=steps
+steps=100,25000,35000
+scales=10,.1,.1
+
+[convolutional]
+batch_normalize=1
+filters=32
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+
+#######
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=1024
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=1024
+activation=leaky
+
+[route]
+layers=-9
+
+[reorg]
+stride=2
+
+[route]
+layers=-1,-3
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=1024
+activation=leaky
+
+[convolutional]
+size=1
+stride=1
+pad=1
+filters=125
+activation=linear
+
+[region]
+anchors = 1.08,1.19,  3.42,4.41,  6.63,11.38,  9.42,5.11,  16.62,10.52
+bias_match=1
+classes=20
+coords=4
+num=5
+softmax=1
+jitter=.2
+rescore=1
+
+object_scale=5
+noobject_scale=1
+class_scale=1
+coord_scale=1
+
+absolute=1
+thresh = .6
+random=0

cfg/yolo-voc.cfg

@@ -11,11 +11,12 @@ saturation = 1.5
 exposure = 1.5
 hue=.1
 
-learning_rate=0.0001
-max_batches = 45000
+learning_rate=0.001
+burn_in=1000
+max_batches = 80200
 policy=steps
-steps=100,25000,35000
-scales=10,.1,.1
+steps=40000,60000
+scales=.1,.1
 
 [convolutional]
 batch_normalize=1
@@ -203,11 +204,19 @@ activation=leaky
 [route]
 layers=-9
 
+[convolutional]
+batch_normalize=1
+size=1
+stride=1
+pad=1
+filters=64
+activation=leaky
+
 [reorg]
 stride=2
 
 [route]
-layers=-1,-3
+layers=-1,-4
 
 [convolutional]
 batch_normalize=1
@@ -224,14 +233,15 @@ pad=1
 filters=125
 activation=linear
 
+
 [region]
-anchors = 1.08,1.19,  3.42,4.41,  6.63,11.38,  9.42,5.11,  16.62,10.52
+anchors =  1.3221, 1.73145, 3.19275, 4.00944, 5.05587, 8.09892, 9.47112, 4.84053, 11.2364, 10.0071
 bias_match=1
 classes=20
 coords=4
 num=5
 softmax=1
-jitter=.2
+jitter=.3
 rescore=1
 
 object_scale=5
@@ -241,4 +251,4 @@ coord_scale=1
 
 absolute=1
 thresh = .6
-random=0
+random=1

cfg/yolo.2.0.cfg

@@ -0,0 +1,244 @@
+[net]
+batch=1
+subdivisions=1
+width=416
+height=416
+channels=3
+momentum=0.9
+decay=0.0005
+angle=0
+saturation = 1.5
+exposure = 1.5
+hue=.1
+
+learning_rate=0.001
+max_batches = 120000
+policy=steps
+steps=-1,100,80000,100000
+scales=.1,10,.1,.1
+
+[convolutional]
+batch_normalize=1
+filters=32
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=64
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[maxpool]
+size=2
+stride=2
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=512
+size=1
+stride=1
+pad=1
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+
+#######
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=1024
+activation=leaky
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=1024
+activation=leaky
+
+[route]
+layers=-9
+
+[reorg]
+stride=2
+
+[route]
+layers=-1,-3
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=1024
+activation=leaky
+
+[convolutional]
+size=1
+stride=1
+pad=1
+filters=425
+activation=linear
+
+[region]
+anchors = 0.738768,0.874946,  2.42204,2.65704,  4.30971,7.04493,  10.246,4.59428,  12.6868,11.8741
+bias_match=1
+classes=80
+coords=4
+num=5
+softmax=1
+jitter=.2
+rescore=1
+
+object_scale=5
+noobject_scale=1
+class_scale=1
+coord_scale=1
+
+absolute=1
+thresh = .6
+random=0

cfg/yolo.cfg

@@ -1,8 +1,8 @@
 [net]
-batch=1
-subdivisions=1
-width=416
-height=416
+batch=64
+subdivisions=8
+height=608
+width=608
 channels=3
 momentum=0.9
 decay=0.0005
@@ -12,10 +12,11 @@ exposure = 1.5
 hue=.1
 
 learning_rate=0.001
-max_batches = 120000
+burn_in=1000
+max_batches = 500200
 policy=steps
-steps=-1,100,80000,100000
-scales=.1,10,.1,.1
+steps=400000,450000
+scales=.1,.1
 
 [convolutional]
 batch_normalize=1
@@ -203,11 +204,19 @@ activation=leaky
 [route]
 layers=-9
 
+[convolutional]
+batch_normalize=1
+size=1
+stride=1
+pad=1
+filters=64
+activation=leaky
+
 [reorg]
 stride=2
 
 [route]
-layers=-1,-3
+layers=-1,-4
 
 [convolutional]
 batch_normalize=1
@@ -224,14 +233,15 @@ pad=1
 filters=425
 activation=linear
 
+
 [region]
-anchors = 0.738768,0.874946,  2.42204,2.65704,  4.30971,7.04493,  10.246,4.59428,  12.6868,11.8741
+anchors =  0.57273, 0.677385, 1.87446, 2.06253, 3.33843, 5.47434, 7.88282, 3.52778, 9.77052, 9.16828
 bias_match=1
 classes=80
 coords=4
 num=5
 softmax=1
-jitter=.2
+jitter=.3
 rescore=1
 
 object_scale=5
@@ -241,4 +251,4 @@ coord_scale=1
 
 absolute=1
 thresh = .6
-random=0
+random=1