Pytorch-yolov3: RuntimeError: shape '[2, 3, 6, 11, 11]' is invalid for input of size 3630

Created on 14 Dec 2019 · 5Comments · Source: eriklindernoren/PyTorch-YOLOv3

Traceback (most recent call last):
File "train.py", line 107, in
loss, outputs = model(imgs, targets)
File "D:\Anaconda\Anaconda_3lib\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-mastermodels.py", line 269, in forward
x, layer_loss = module0
File "D:\Anaconda\Anaconda_3lib\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-mastermodels.py", line 153, in forward
x.view(num_samples, self.num_anchors, self.num_classes + 5, grid_size, grid_size)

RuntimeError: shape '[2, 3, 6, 11, 11]' is invalid for input of size 3630

this is my error
please,help me

Source

AadeIT

Most helpful comment

Change your configuration file，find [yolo]，A total of three

Here's the part code

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

[convolutional]
size=1
stride=1
pad=1
filters=15 #change this，A total of three，（5+your classes num *6
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

------------------ 原始邮件 ------------------
发件人: "ischansgithub"<[email protected]>;
发送时间: 2019年12月24日(星期二) 中午1:28
收件人: "eriklindernoren/PyTorch-YOLOv3"<[email protected]>;
抄送: "1342868324"<[email protected]>;"Author"<[email protected]>;
主题: Re: [eriklindernoren/PyTorch-YOLOv3] RuntimeError: shape '[2, 3, 6, 11, 11]' is invalid for input of size 3630 (#378)

same

—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub, or unsubscribe.

AadeIT on 24 Dec 2019

👍4 ❤1

All 5 comments

same

ischansgithub on 24 Dec 2019

Change your configuration file，find yolov3，A total of three

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

[convolutional]
size=1
stride=1
pad=1
filters=15 #change this
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 on 24 Dec 2019

👍2

Change your configuration file，find [yolo]，A total of three

Here's the part code

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

[convolutional]
size=1
stride=1
pad=1
filters=15 #change this，A total of three，（5+your classes num *6
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

same

—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub, or unsubscribe.

AadeIT on 24 Dec 2019

👍4 ❤1

Change your configuration file，find [yolo]，A total of three Here's the part code ************ [convolutional] batch_normalize=1 size=3 stride=1 pad=1 filters=256 activation=leaky [convolutional] size=1 stride=1 pad=1 filters=15 #change this，A total of three，（5+your classes num *6 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 ******
…
------------------ 原始邮件 ------------------ 发件人: "ischansgithub"<[email protected]>; 发送时间: 2019年12月24日(星期二) 中午1:28 收件人: "eriklindernoren/PyTorch-YOLOv3"<[email protected]>; 抄送: "1342868324"<[email protected]>;"Author"<[email protected]>; 主题: Re: [eriklindernoren/PyTorch-YOLOv3] RuntimeError: shape '[2, 3, 6, 11, 11]' is invalid for input of size 3630 (#378) same — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.

Your answer solved my problem. Thank you!!!!

ischansgithub on 24 Dec 2019

you're welcome
------------------ 原始邮件 ------------------
发件人: "ischansgithub"<[email protected]>;
发送时间: 2019年12月24日(星期二) 中午1:56
收件人: "eriklindernoren/PyTorch-YOLOv3"<[email protected]>;
抄送: "1342868324"<[email protected]>;"Author"<[email protected]>;
主题: Re: [eriklindernoren/PyTorch-YOLOv3] RuntimeError: shape '[2, 3, 6, 11, 11]' is invalid for input of size 3630 (#378)

Change your configuration file，find [yolo]，A total of three Here's the part code ************ [convolutional] batch_normalize=1 size=3 stride=1 pad=1 filters=256 activation=leaky [convolutional] size=1 stride=1 pad=1 filters=15 #change this，A total of three，（5+your classes num *6 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 ******
…
------------------ 原始邮件 ------------------ 发件人: "ischansgithub"<[email protected]>; 发送时间: 2019年12月24日(星期二) 中午1:28 收件人: "eriklindernoren/PyTorch-YOLOv3"<[email protected]>; 抄送: "1342868324"<[email protected]>;"Author"<[email protected]>; 主题: Re: [eriklindernoren/PyTorch-YOLOv3] RuntimeError: shape '[2, 3, 6, 11, 11]' is invalid for input of size 3630 (#378) same — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.