"model_data/CSPdarknet53_backbone_weights.pth"

[hejunran]

请问这个文件有嘛

[infochen]

百度网盘有，但是我加载这个权重会出错，但其他两个不会

initialize network with normal type Load weights model_data/CSPdarknet53_backbone_weights.pth. Traceback (most recent call last): File "train.py", line 153, in pretrained_dict = {k: v for k, v in pretrained_dict.items() if np.shape(model_dict[k]) == np.shape(v)} File "train.py", line 153, in pretrained_dict = {k: v for k, v in pretrained_dict.items() if np.shape(model_dict[k]) == np.shape(v)} KeyError: 'conv1.conv.weight'

[XuecWu]

@infochen 看问题是权值不匹配，看一下动backbone了没有

[infochen]

收到

[XuecWu]

@hejunran release里面有

[hejunran]

嗯嗯 ------------------ 原始邮件 ------------------ 发件人: "bubbliiiing/yolov4-pytorch" @.>; 发送时间: 2022年2月27日(星期天) 中午11:41 @.>; @.@.>; 主题: Re: [bubbliiiing/yolov4-pytorch] "model_data/CSPdarknet53_backbone_weights.pth" (Issue #264)

百度网盘有，但是我加载这个权重会出错，但其他两个不会

initialize network with normal type Load weights model_data/CSPdarknet53_backbone_weights.pth. Traceback (most recent call last): File "train.py", line 153, in pretrained_dict = {k: v for k, v in pretrained_dict.items() if np.shape(model_dict[k]) == np.shape(v)} File "train.py", line 153, in pretrained_dict = {k: v for k, v in pretrained_dict.items() if np.shape(model_dict[k]) == np.shape(v)} KeyError: 'conv1.conv.weight'

— Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android. You are receiving this because you authored the thread.Message ID: @.***>

[bubbliiiing]

是pretrain=True调用。

[hejunran]

好的，谢谢up主

------------------ 原始邮件 ------------------ 发件人: "bubbliiiing/yolov4-pytorch" @.>; 发送时间: 2022年3月5日(星期六) 中午1:51 @.>; @.@.>; 主题: Re: [bubbliiiing/yolov4-pytorch] "model_data/CSPdarknet53_backbone_weights.pth" (Issue #264)

是pretrain=True调用。

— Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android. You are receiving this because you were mentioned.Message ID: @.***>