RuntimeError: Error(s) in loading state_dict for SSD: #3
Comments
|
Can you share with me the download address of opixray dataset？thanks！！ |
|
我也想要一份数据集地址，求求了，谢谢！ |
|
我也遇到了这个维度问题，请问您解决了么，是直接将vgg的输入改成4通道么，期待您的回复！ |
|
I also encountered this dimension problem. Did you solve it? Did you directly change the input of vgg to 4 channels? Looking forward to your reply! |
|
有截图吗，我有点不太记得这个问题了
…------------------ 原始邮件 ------------------
发件人: "OPIXray-author/OPIXray" ***@***.***>;
发送时间: 2022年8月17日(星期三) 晚上6:58
***@***.***>;
***@***.******@***.***>;
主题: Re: [OPIXray-author/OPIXray] RuntimeError: Error(s) in loading state_dict for SSD: (#3)
我也遇到了这个维度问题，请问您解决了么，是直接将vgg的输入改成4通道么，期待您的回复！
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you commented.Message ID: ***@***.***>
|
|
|
我尝试过将DOAM模块转到别的框架上但是没有成功，后来我直接放弃了使用这个模块，而对于这个论文我只是跑通看了效果之后没有做出改进，所以很抱歉不能回答你的问题，我太菜了，祝你早日解决问题
…------------------ 原始邮件 ------------------
发件人: "OPIXray-author/OPIXray" ***@***.***>;
发送时间: 2022年8月18日(星期四) 中午12:08
***@***.***>;
***@***.******@***.***>;
主题: Re: [OPIXray-author/OPIXray] RuntimeError: Error(s) in loading state_dict for SSD: (#3)
有截图吗，我有点不太记得这个问题了
…
------------------ 原始邮件 ------------------ 发件人: "OPIXray-author/OPIXray" @.>; 发送时间: 2022年8月17日(星期三) 晚上6:58 @.>; @.@.>; 主题: Re: [OPIXray-author/OPIXray] RuntimeError: Error(s) in loading state_dict for SSD: (#3) 我也遇到了这个维度问题，请问您解决了么，是直接将vgg的输入改成4通道么，期待您的回复！ — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: @.***>
非常感谢您的回复，就是 forward() 中输入tensor首先经过了这个“self.edge_conv2d()”，也就是DOAM模块，输出是一个4通道的tensor，但是vgg的第一个卷积就是3通道的 “self.vgg[0] ：Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))”所以出现了这个错误，我的做法是在DOAM模块的最后一层添加了一个卷积“torch.nn.Conv2d(4, 3, kernel_size=3, padding=1)”，请问您是怎么解决的呢，另外我把这个DOAM模块迁移到了yolov5上，训练速度异常的慢，请问您遇到过么，这是合理的么。
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you commented.Message ID: ***@***.***>
|
|
同样感谢您的回复，最近在做安检的目标检测任务，感觉好难啊，感谢回复 |
|
谁不是我每天感觉自己毕不了业，天天摆烂
…------------------ 原始邮件 ------------------
发件人: "OPIXray-author/OPIXray" ***@***.***>;
发送时间: 2022年8月18日(星期四) 中午1:38
***@***.***>;
***@***.******@***.***>;
主题: Re: [OPIXray-author/OPIXray] RuntimeError: Error(s) in loading state_dict for SSD: (#3)
同样感谢您的回复，最近在做安检的目标检测任务，感觉好难啊，感谢回复
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you commented.Message ID: ***@***.***>
|
|
可以多交流，好难，祝好 |
|
是这个方向很难吗还是创新很难呢 |
Traceback (most recent call last):
File "test.py", line 592, in
net.load_state_dict(torch.load(args.trained_model))
File "E:\Aftab\X-Ray-Baggage-Scanning\OPIXray\env\lib\site-packages\torch\nn\modules\module.py", line 830, in load_state_dict
self.class.name, "\n\t".join(error_msgs)))
RuntimeError: Error(s) in loading state_dict for SSD:
Missing key(s) in state_dict: "_conf.0.weight", "_conf.0.bias", "_conf.1.weight", "_conf.1.bias", "_conf.2.weight", "_conf.2.bias", "_conf.3.weight", "_conf.3.bias", "_conf.4.weight", "_conf.4.bias", "_conf.5.weight", "_conf.5.bias", "edge_conv2d.weight_const_hori", "edge_conv2d.weight_hori", "edge_conv2d.gamma", "edge_conv2d.weight_const_vertical", "edge_conv2d.weight_vertical", "edge_conv2d.conv2d_1_1.conv2d_1_1.weight", "edge_conv2d.conv2d_1_1.conv2d_1_1.bias", "edge_conv2d.conv2d_1_attention.conv2d_1_attention.weight", "edge_conv2d.conv2d_1_attention.conv2d_1_attention.bias", "edge_conv2d.conv2d_2_attention.conv2d_2_attention.weight", "edge_conv2d.conv2d_2_attention.conv2d_2_attention.bias", "edge_conv2d.conv2d_3_attention.conv2d_3_attention.weight", "edge_conv2d.conv2d_3_attention.conv2d_3_attention.bias", "edge_conv2d.conv2d_4_attention.conv2d_4_attention.weight", "edge_conv2d.conv2d_4_attention.conv2d_4_attention.bias", "edge_conv2d.conv2d_5_attention.conv2d_5_attention.weight", "edge_conv2d.conv2d_5_attention.conv2d_5_attention.bias", "edge_conv2d.conv2d_1_rgb_attention.conv2d_1_rgb_attention.weight", "edge_conv2d.conv2d_1_rgb_attention.conv2d_1_rgb_attention.bias", "edge_conv2d.conv2d_2_rgb_attention.conv2d_2_rgb_attention.weight", "edge_conv2d.conv2d_2_rgb_attention.conv2d_2_rgb_attention.bias", "edge_conv2d.conv2d_3_rgb_attention.conv2d_3_rgb_attention.weight", "edge_conv2d.conv2d_3_rgb_attention.conv2d_3_rgb_attention.bias", "edge_conv2d.conv2d_4_rgb_attention.conv2d_4_rgb_attention.weight", "edge_conv2d.conv2d_4_rgb_attention.conv2d_4_rgb_attention.bias", "edge_conv2d.conv2d_5_rgb_attention.conv2d_5_rgb_attention.weight", "edge_conv2d.conv2d_5_rgb_attention.conv2d_5_rgb_attention.bias", "edge_conv2d.GatedConv2dWithActivation.conv2d.weight", "edge_conv2d.GatedConv2dWithActivation.conv2d.bias", "edge_conv2d.GatedConv2dWithActivation.mask_conv2d.weight", "edge_conv2d.GatedConv2dWithActivation.mask_conv2d.bias", "edge_conv2d.GatedConv2dWithActivation.batch_norm2d.weight", "edge_conv2d.GatedConv2dWithActivation.batch_norm2d.bias", "edge_conv2d.GatedConv2dWithActivation.batch_norm2d.running_mean", "edge_conv2d.GatedConv2dWithActivation.batch_norm2d.running_var", "edge_conv2d.conv2d_1_rgb_red_concat_5.conv2d_1_rgb_red_concat_5.weight", "edge_conv2d.conv2d_1_rgb_red_concat_5.conv2d_1_rgb_red_concat_5.bias", "edge_conv2d.conv2d_1_rgb_red_concat_10.conv2d_1_rgb_red_concat_10.weight", "edge_conv2d.conv2d_1_rgb_red_concat_10.conv2d_1_rgb_red_concat_10.bias", "edge_conv2d.conv2d_1_rgb_red_concat_15.conv2d_1_rgb_red_concat_15.weight", "edge_conv2d.conv2d_1_rgb_red_concat_15.conv2d_1_rgb_red_concat_15.bias".
Unexpected key(s) in state_dict: "conf.0.weight", "conf.0.bias", "conf.1.weight", "conf.1.bias", "conf.2.weight", "conf.2.bias", "conf.3.weight", "conf.3.bias", "conf.4.weight", "conf.4.bias", "conf.5.weight", "conf.5.bias".
size mismatch for vgg.0.weight: copying a param with shape torch.Size([64, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([64, 4, 3, 3]).
@OPIXray-author why it is showing such error while loading the SSD model?
The text was updated successfully, but these errors were encountered: