Error: l.outputs == params.inputs filters= in the [convolutional]-layer doesn't correspond to classes= or mask= in [yolo]-layer #2263
Comments
|
did you solve it? |
|
use the filter formula for convolution layer before YOLO layer (classes+5)x3 so the filter not 255 but 18, (1+5)x3 |
|
the questions is here (80+4+1)*3=255 [convolutional]
size=1
stride=1
pad=1
filters=18
activation=linear
[yolo]
mask = 3,4,5
anchors = 10,14, 23,27, 37,58, 81,82, 135,169, 344,319
classes=80
num=6
jitter=.3
scale_x_y = 1.05
cls_normalizer=1.0
iou_normalizer=0.07
iou_loss=ciou
ignore_thresh = .7
truth_thresh = 1
random=0
resize=1.5
nms_kind=greedynms
beta_nms=0.6
... |
|
I used this according to the formula but it's still giving errors? |
|
The following comment is true. You need to add one more thing. so the filter not 255 but 18, (1+5)x3" AS I saw your code you should first change your classes=1 this should happens in three lines: |
|
I am getting the same error. Can anyone please help. I have 5 classes [net] Testing#batch=1 Trainingbatch=64 learning_rate=0.001 #cutmix=1 #:104x104 54:52x52 85:26x26 104:13x13 for 416 [convolutional] Downsample[convolutional] [convolutional] [route] [convolutional] [convolutional] [convolutional] [shortcut] [convolutional] [route] [convolutional] Downsample[convolutional] [convolutional] [route] [convolutional] [convolutional] [convolutional] [shortcut] [convolutional] [convolutional] [shortcut] [convolutional] [route] [convolutional] Downsample[convolutional] [convolutional] [route] [convolutional] [convolutional] [convolutional] [shortcut] [convolutional] [convolutional] [shortcut] [convolutional] [convolutional] [shortcut] [convolutional] [convolutional] [shortcut] [convolutional] [convolutional] [shortcut] [convolutional] [convolutional] [shortcut] [convolutional] [convolutional] [shortcut] [convolutional] [convolutional] [shortcut] [convolutional] [route] [convolutional] Downsample[convolutional] [convolutional] [route] [convolutional] [convolutional] [convolutional] [shortcut] [convolutional] [convolutional] [shortcut] [convolutional] [convolutional] [shortcut] [convolutional] [convolutional] [shortcut] [convolutional] [convolutional] [shortcut] [convolutional] [convolutional] [shortcut] [convolutional] [convolutional] [shortcut] [convolutional] [convolutional] [shortcut] [convolutional] [route] [convolutional] Downsample[convolutional] [convolutional] [route] [convolutional] [convolutional] [convolutional] [shortcut] [convolutional] [convolutional] [shortcut] [convolutional] [convolutional] [shortcut] [convolutional] [convolutional] [shortcut] [convolutional] [route] [convolutional] ########################## [convolutional] [convolutional] [convolutional] SPP[maxpool] [route] [maxpool] [route] [maxpool] [route] End SPP[convolutional] [convolutional] [convolutional] [convolutional] [upsample] [route] [convolutional] [route] [convolutional] [convolutional] [convolutional] [convolutional] [convolutional] [convolutional] [upsample] [route] [convolutional] [route] [convolutional] [convolutional] [convolutional] [convolutional] [convolutional] ########################## [convolutional] [convolutional] [yolo] [route] [convolutional] [route] [convolutional] [convolutional] [convolutional] [convolutional] [convolutional] [convolutional] [convolutional] [yolo] [route] [convolutional] [route] [convolutional] [convolutional] [convolutional] [convolutional] [convolutional] [convolutional] [convolutional] [yolo] |
|
In this code block you need to make the filters 30 If I remember correctly this part is in 3 or 4 places. Fixing these fixed my problem. |
|
Why, if I correctly specify the number of filters, then YOLO v3 works, but does not recognize? The same Python model recognizes |
|
filters = (classes + 5) * 3 |
Trying to train a YoloV4 Tiny darknet model for 1 class and this error pops up. Here's my cfg file.
[net]
Testing
#batch=1
#subdivisions=1
Training
batch=64
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=0.00261
burn_in=1000
max_batches = 500200
policy=steps
steps=400000,450000
scales=.1,.1
[convolutional]
batch_normalize=1
filters=32
size=3
stride=2
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=64
size=3
stride=2
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=64
size=3
stride=1
pad=1
activation=leaky
[route]
layers=-1
groups=2
group_id=1
[convolutional]
batch_normalize=1
filters=32
size=3
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=32
size=3
stride=1
pad=1
activation=leaky
[route]
layers = -1,-2
[convolutional]
batch_normalize=1
filters=64
size=1
stride=1
pad=1
activation=leaky
[route]
layers = -6,-1
[maxpool]
size=2
stride=2
[convolutional]
batch_normalize=1
filters=128
size=3
stride=1
pad=1
activation=leaky
[route]
layers=-1
groups=2
group_id=1
[convolutional]
batch_normalize=1
filters=64
size=3
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=64
size=3
stride=1
pad=1
activation=leaky
[route]
layers = -1,-2
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky
[route]
layers = -6,-1
[maxpool]
size=2
stride=2
[convolutional]
batch_normalize=1
filters=256
size=3
stride=1
pad=1
activation=leaky
[route]
layers=-1
groups=2
group_id=1
[convolutional]
batch_normalize=1
filters=128
size=3
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=128
size=3
stride=1
pad=1
activation=leaky
[route]
layers = -1,-2
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky
[route]
layers = -6,-1
[maxpool]
size=2
stride=2
[convolutional]
batch_normalize=1
filters=512
size=3
stride=1
pad=1
activation=leaky
##################################
[convolutional]
batch_normalize=1
filters=18
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=18
size=3
stride=1
pad=1
activation=leaky
[convolutional]
size=1
stride=1
pad=1
filters=18
activation=linear
[yolo]
mask = 3,4,5
anchors = 10,14, 23,27, 37,58, 81,82, 135,169, 344,319
classes=80
num=6
jitter=.3
scale_x_y = 1.05
cls_normalizer=1.0
iou_normalizer=0.07
iou_loss=ciou
ignore_thresh = .7
truth_thresh = 1
random=0
resize=1.5
nms_kind=greedynms
beta_nms=0.6
[route]
layers = -4
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky
[upsample]
stride=2
[route]
layers = -1, 23
[convolutional]
batch_normalize=1
filters=256
size=3
stride=1
pad=1
activation=leaky
[convolutional]
size=1
stride=1
pad=1
filters=255
activation=linear
[yolo]
mask = 0,1,2
anchors = 10,14, 23,27, 37,58, 81,82, 135,169, 344,319
classes=80
num=6
jitter=.3
scale_x_y = 1.05
cls_normalizer=1.0
iou_normalizer=0.07
iou_loss=ciou
ignore_thresh = .7
truth_thresh = 1
random=0
resize=1.5
nms_kind=greedynms
beta_nms=0.6
Can anyone solve the problem? Thanks.
The text was updated successfully, but these errors were encountered: