Mr.Li
Mr.Li
> /basicsr/ops/dcn/deform_conv.py error in line 144 This file is always wrong, what should I do Has this problem been solved? I meet the same problem when test.
I did some experiments. For example, I followed the steps below to generate a texture map as shown in the figure below： “If you want a texture, you first need...
Hi have u resolve it?
> Hello, do you know how to generate this normalized_proposal_list.txt on other videos > @suhaisheng have u resolved it?
https://file.lzhu.me/projects/tsm/models/TSM_kinetics_RGB_resnet50_shift8_blockres_avg_segment8_e100_dense.pth
以上问题用新版本的代码可以无错误跑了。但是又遇到了新的问题没有能够解决，请您帮忙分析一下： 我在自己生成的数据集上微调另一个项目里的模型，迭代一两次之后准确率还可以，val识别也是正确的，如图：  但是我用微调后的模型去识别测试图像，输出是错误的（乱码的），如图：  图中netCRNN63.pth为预训练模型，crnn_best.pth为微调后的。 可以请您帮忙分析一下吗，谢谢！！
> I have the same problem@425183525 , do you solve it? I have the same problem,did you solve it?
> @wenlihaoyu 作者你好，这keras-yolo利用自己数据微调训练，请问如何冻结相关层，需要冻结哪几层？谢谢 请问您这个问题解决了吗，冻结哪些层呢
请问提供的预训练模型是在那个数据集上进行训练的？
> > Hi @RonanDou The "detection_results.txt" file is the txt format of the json file after post-processing. > > You may need to change the line here. > > https://github.com/frostinassiky/gtad/blob/6deb5b1bc6883b48bd22e0cc593069643c953e3d/gtad_postprocess.py#L154-L156...