PyTorch-YOLOv3 icon indicating copy to clipboard operation
PyTorch-YOLOv3 copied to clipboard

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

Open AadeIT opened this issue 5 years ago • 5 comments

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

this is my error please,help me

AadeIT avatar Dec 14 '19 16:12 AadeIT

same

chenwwayne avatar Dec 24 '19 05:12 chenwwayne

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 avatar Dec 24 '19 05:12 AadeIT

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 avatar Dec 24 '19 05:12 AadeIT

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!!!!

chenwwayne avatar Dec 24 '19 05:12 chenwwayne

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.

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

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

AadeIT avatar Dec 24 '19 06:12 AadeIT