RuntimeError: shape '[4, 3, 6, 11, 11]' is invalid for input of size 7260

[AadeIT]

please，help me

[FLyingLSJ]

Could you put a screenshot with error

[AadeIT]

Namespace(batch_size=4, checkpoint_interval=1, compute_map=False, data_config='config/custom.data', epochs=100, evaluation_interval=1, gradient_accumulations=2, img_size=416, model_def
='config/yolov3-custom.cfg', multiscale_training=True, n_cpu=8, pretrained_weights='weights/darknet53.conv.74')
Traceback (most recent call last):
File "train.py", line 107, in
loss, outputs = model(imgs, targets)
File "D:\Anaconda\Anaconda_3\lib\site-packages\torch\nn\modules\module.py", line 541, in call
result = self.forward(*input, **kwargs)
File "D:\pytoch\PyTorch-YOLOv3-master (3)\PyTorch-YOLOv3-master\models.py", line 269, in forward
x, layer_loss = module[0](x, targets, img_dim)
File "D:\Anaconda\Anaconda_3\lib\site-packages\torch\nn\modules\module.py", line 541, in call
result = self.forward(*input, **kwargs)
File "D:\pytoch\PyTorch-YOLOv3-master (3)\PyTorch-YOLOv3-master\models.py", line 153, in forward
x.view(num_samples, self.num_anchors, self.num_classes + 5, grid_size, grid_size)
RuntimeError: shape '[4, 3, 6, 11, 11]' is invalid for input of size 7260

this is my error！

[FLyingLSJ]

The input image size should be 32*n, for example 64, 128, 448 etc

[AadeIT]

I useing datasets name is DETRAC，image size is 960*540,You mean I change the size of the picture?

[FLyingLSJ]

You can try this image size: 960*544. Because of 544/32=17.

[AadeIT]

I changed the image size to 960*544, batch_size=2(I only have two pictures in my training folder, try to see if I can run through), but the problem is still this error

[FLyingLSJ]

check you yolov3-custom.cfg file The error is 4*3*6*11*11 not equal 7260

…

---Original--- From: "AadeIT"<[email protected]&gt; Date: 2019/12/14 23:32:38 To: "FLyingLSJ/Computer_Vision_Project"<[email protected]&gt;; Cc: "Comment"<[email protected]&gt;;"Leong"<[email protected]&gt;; Subject: Re: [FLyingLSJ/Computer_Vision_Project] RuntimeError: shape '[4, 3, 6, 11, 11]' is invalid for input of size 7260 (#3) Namespace(batch_size=4, checkpoint_interval=1, compute_map=False, data_config='config/custom.data', epochs=100, evaluation_interval=1, gradient_accumulations=2, img_size=416, model_def ='config/yolov3-custom.cfg', multiscale_training=True, n_cpu=8, pretrained_weights='weights/darknet53.conv.74') Traceback (most recent call last): File "train.py", line 107, in loss, outputs = model(imgs, targets) File "D:\Anaconda\Anaconda_3\lib\site-packages\torch\nn\modules\module.py", line 541, in call result = self.forward(*input, **kwargs) File "D:\pytoch\PyTorch-YOLOv3-master (3)\PyTorch-YOLOv3-master\models.py", line 269, in forward x, layer_loss = module[0](x, targets, img_dim) File "D:\Anaconda\Anaconda_3\lib\site-packages\torch\nn\modules\module.py", line 541, in call result = self.forward(*input, **kwargs) File "D:\pytoch\PyTorch-YOLOv3-master (3)\PyTorch-YOLOv3-master\models.py", line 153, in forward x.view(num_samples, self.num_anchors, self.num_classes + 5, grid_size, grid_size) RuntimeError: shape '[4, 3, 6, 11, 11]' is invalid for input of size 7260 this is my error！ — You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe.

[AadeIT]

There's no way to think about these parameters, so let me think about it again. Thank you

[xiaoyuzhu666]

please，help me

Hi，I got the same error，did you solve it？

[AadeIT]

@xiaoyuzhu666 try,change your filters of config file

[xiaoyuzhu666]

Thanks,but I have changed it, the error still exist(filters=18,class=1)😭

…

---Original--- From: "AadeIT"<[email protected]&gt; Date: Wed, Apr 1, 2020 16:33 PM To: "FLyingLSJ/Computer_Vision_Project"<[email protected]&gt;; Cc: "xiaoyuzhu666"<[email protected]&gt;;"Mention"<[email protected]&gt;; Subject: Re: [FLyingLSJ/Computer_Vision_Project] RuntimeError: shape '[4, 3, 6, 11, 11]' is invalid for input of size 7260 (#3) @xiaoyuzhu666 try,change your filters of config file — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or unsubscribe.

[AadeIT]

@xiaoyuzhu666
filters of config file
A total of three
find [yolo]

[convolutional]
size=1
stride=1
pad=1
filters=255 <---------------------- change this filters ,filters = (classes+5)*3
activation=linear

[yolo]
mask = 0,1,2
anchors = 10,13, 16,30, 33,23, 30,61, 62,45, 59,119, 116,90, 156,198, 373,326
classes=80
num=9
jitter=.3
ignore_thresh = .7
truth_thresh = 1
random=1

[AadeIT]

@xiaoyuzhu666 That's how I solved my error

[xiaoyuzhu666]

@xiaoyuzhu666
filters of config file
A total of three
find [yolo]

[convolutional]
size=1
stride=1
pad=1
filters=255 <---------------------- change this filters ,filters = (classes+5)*3
activation=linear

[yolo]
mask = 0,1,2
anchors = 10,13, 16,30, 33,23, 30,61, 62,45, 59,119, 116,90, 156,198, 373,326
classes=80
num=9
jitter=.3
ignore_thresh = .7
truth_thresh = 1
random=1

I don‘t know if it is related to “anchors”：
[convolutional]
size=1
stride=1
pad=1
filters=18
activation=linear

[yolo]
mask = 0 *********0/1/2
anchors = 65,65, 97,97, 162,162
classes=1
num=3
jitter=.3
ignore_thresh = .5
truth_thresh = 1
random=1

[FLyingLSJ]

@xiaoyuzhu666
if you have 3 class ,you can try this cfg!

# Testing
#batch=1
#subdivisions=1
# Training
batch=16
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
burn_in=1000
max_batches = 500200
policy=steps
steps=400000,450000
scales=.1,.1

[convolutional]
batch_normalize=1
filters=32
size=3
stride=1
pad=1
activation=leaky

# Downsample

[convolutional]
batch_normalize=1
filters=64
size=3
stride=2
pad=1
activation=leaky

[convolutional]
batch_normalize=1
filters=32
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
filters=64
size=3
stride=1
pad=1
activation=leaky

[shortcut]
from=-3
activation=linear

# Downsample

[convolutional]
batch_normalize=1
filters=128
size=3
stride=2
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

[shortcut]
from=-3
activation=linear

[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

[shortcut]
from=-3
activation=linear

# Downsample

[convolutional]
batch_normalize=1
filters=256
size=3
stride=2
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

[shortcut]
from=-3
activation=linear

[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

[shortcut]
from=-3
activation=linear

[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

[shortcut]
from=-3
activation=linear

[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

[shortcut]
from=-3
activation=linear


[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

[shortcut]
from=-3
activation=linear

[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

[shortcut]
from=-3
activation=linear

[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

[shortcut]
from=-3
activation=linear

[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

[shortcut]
from=-3
activation=linear

# Downsample

[convolutional]
batch_normalize=1
filters=512
size=3
stride=2
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

[shortcut]
from=-3
activation=linear


[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

[shortcut]
from=-3
activation=linear


[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

[shortcut]
from=-3
activation=linear


[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

[shortcut]
from=-3
activation=linear

[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

[shortcut]
from=-3
activation=linear


[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

[shortcut]
from=-3
activation=linear


[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

[shortcut]
from=-3
activation=linear

[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

[shortcut]
from=-3
activation=linear

# Downsample

[convolutional]
batch_normalize=1
filters=1024
size=3
stride=2
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

[shortcut]
from=-3
activation=linear

[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

[shortcut]
from=-3
activation=linear

[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

[shortcut]
from=-3
activation=linear

[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

[shortcut]
from=-3
activation=linear

######################

[convolutional]
batch_normalize=1
filters=512
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=1024
activation=leaky

[convolutional]
batch_normalize=1
filters=512
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=1024
activation=leaky

[convolutional]
batch_normalize=1
filters=512
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=1024
activation=leaky

[convolutional]
size=1
stride=1
pad=1
filters=18 # filters = (classes+5)*3
activation=linear


[yolo]
mask = 6,7,8
anchors = 10,13,  16,30,  33,23,  30,61,  62,45,  59,119,  116,90,  156,198,  373,326
classes=1
num=9
jitter=.3
ignore_thresh = .7
truth_thresh = 1
random=1


[route]
layers = -4

[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky

[upsample]
stride=2

[route]
layers = -1, 61



[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=512
activation=leaky

[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=512
activation=leaky

[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=512
activation=leaky

[convolutional]
size=1
stride=1
pad=1
filters=18 # filters = (classes+5)*3
activation=linear


[yolo]
mask = 3,4,5
anchors = 10,13,  16,30,  33,23,  30,61,  62,45,  59,119,  116,90,  156,198,  373,326
classes=1
num=9
jitter=.3
ignore_thresh = .7
truth_thresh = 1
random=1



[route]
layers = -4

[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky

[upsample]
stride=2

[route]
layers = -1, 36



[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=256
activation=leaky

[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=256
activation=leaky

[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky

[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=256
activation=leaky

[convolutional]
size=1
stride=1
pad=1
filters=18 # filters = (classes+5)*3
activation=linear


[yolo]
mask = 0,1,2
anchors = 10,13,  16,30,  33,23,  30,61,  62,45,  59,119,  116,90,  156,198,  373,326
classes=1
num=9
jitter=.3
ignore_thresh = .7
truth_thresh = 1
random=1

[AadeIT]

@xiaoyuzhu666 Has nothing to do with the anchor

[xiaoyuzhu666]

@xiaoyuzhu666 Has nothing to do with the anchor

I changed “anchors”and “num” using k-means clustering，，，the number of anchor is 3（not 9）
[yolo]
mask = 0
anchors = 65,65, 97,97, 162,162
classes=1
num=3

[AadeIT]

@xiaoyuzhu666
I think you useing the default anchors
K-means clustering in yolo v2 ,not yolov3

[xiaoyuzhu666]

@xiaoyuzhu666
I think you useing the default anchors
K-means clustering in yolo v2 ,not yolov3

0.0
Oh！！！Thank you！