justlovebarbecue
justlovebarbecue
@bneelon85 sorry for the so late reply, did you make it? @jintianchen , i remembered that there are several datasets provided in their official version, what I did is find...
@xjtushujun @jingzhengli 您好，我也是看到这个地方，有些不理解。meta_model 本身是不包含vnet的，vnet的梯度是怎么计算出来的呢？我发现meta_model.update_params这行代码应该很重要，我去掉这行，vnet的梯度就不能计算了。可是这行代码调用的函数 只和meta_model相关，是怎么能和vnet有联系的呢？如果方便 麻烦讲解一下，谢谢您！
Hi, I have revised your code and feed my own data into model, however, I obtained a low accuracy like around 20%. My dataset is about time series classification with...
Hi, thx for reply. I have 3 views time series data. I directly revised your code "test_mosi.py": comment your "load_saved_data" function and load my own data with shape (num_of _sample,...
Hi, Thank you so much for your kind reply. Will have a try following your hints. THX!
OK! Thanks for your advice! Will try it! :)
Hi, I noticed that there is another method called "EFLSTM". Is that just a basic LSTM model using concatenated data along with the feature dimension from different views? I have...
@A2Zadeh OK. Got it. Thank you so much!
Hi @A2Zadeh , I am trying to replicate your results on Youtube dataset. I have some questions below: 1. Can I use the same "test_mosi.py" to do that? 2. Could...
I met the same issue, I think the lora_scale should be (lora_alpha / lora_rank)? which is indicated during lora finetuning, however, after doing so, the testing results are still different...