MachineLearning11

Results 9 comments of MachineLearning11

@pcshih How to solve the problem? Although it has been a long time, I hope I can help answer it if I can. Thank you

> I can only get about 76% on UCF-101 split 1 testing dataset and the model seems overfitting... How can I fix the overfitting problem? > > ![loss](https://user-images.githubusercontent.com/48461528/72399005-d9a40200-377f-11ea-9ac4-568eb83ecd56.JPG) ![acc](https://user-images.githubusercontent.com/48461528/72399006-d9a40200-377f-11ea-9a35-2430bb6269a6.JPG) 你好我的结果也是76%的准确率,请问你是如何解决的,是否使用与训练模型还是修改了网络代码?失望可以得到恢复,谢谢!

请问是如何解决的,我看到许多代码都没有管理这个问题,希望可以得到解决? How to solve this problem? I see that many codes are not managed. I hope it can be solved

> same questions How to solve this problem? I see that many codes are not managed. I hope it can be solved

> # step 8 > ``` > util.generate_proposal_step2_from_step1() > ``` > > 这一步 model_step1_final.pt 用model_step1_8.pt代替了 > > 但是train_data_with_crop_step1.pkl 这个文件好像一直没有生成? > > 请问是哪一步的生成文件? 请问 你解决这个问题了吗?希望可以教一下

> 我正在尝试基于转换器重构您的模型,但我遇到了一个问题:某处总是有错误,但我尝试了很多解决方案,但我不知道。 ![图片](https://user-images.githubusercontent.com/36957508/157254342-ea56e0ae-78cc-4531-a3ba-43ba6246e304.png) > > ``` > class ClipCaptionModel(PreTrainedModel): > def __init__(self, config): > super(ClipCaptionModel, self).__init__(config) > self.prefix_length = config.prefix_length > self.clip_length = config.clip_length > self.prefix_size = config.prefix_size > self.num_layers...

> 而这也已经是这几个脚本里面报错最不邪乎,最有可能跑起来的一个了 请问这个如何修改

> How to download the model files? l also want to know