wanzhixiao
wanzhixiao
修改了TransferLearningGame.py, 以flag列作为标签,可以运行。但是AUC很低 ``` # cody by chenchiwei # -*- coding: UTF-8 -*- import pandas as pd from sklearn import preprocessing from sklearn import decomposition import trad1 as tr import TrAdaboost...
> 我做了一个PyTorch版本,没有做任何修改。这是我的代码:[https](https://github.com/hazdzz/STGCN) : [//github.com/hazdzz/STGCN](https://github.com/hazdzz/STGCN) how do you guarantee your implementation follow the paper?
does this implementation of temporal convoution module correct? class temporal_conv_layer(nn.Module): def __init__(self, Kt, c_in, c_out): ''' :param Kt: int, kernel size of temporal convolution. :param c_in: int, size of input...
> > does this implementation of temporal convoution module correct? > > class temporal_conv_layer(nn.Module): > > ``` > > def __init__(self, Kt, c_in, c_out): > > ''' > > :param...
> 微调后也可以用方式4的,模型结构是一致的。 可以直接用4部署微调后的模型吗,现在外面套了一层FlagModel,怎么转成huggingface格式 模型?
> 损失函数是否采用的是有监督S 可以贴一些微调代码的链接吗
> Hi @Narsil,Thanks for commenting. Before parallelisation, I wanted to benchmark the time whether text-embeddings-inference make inference faster or not. That' why I had used same documents and same approach...
> > @guokan987 Hi! I'm confused about this code? Does it mean AX? > > ``` > > class nconv(nn.Module): > > def __init__(self): > > super(nconv,self).__init__() > > >...
> Hi,I see you use keras==2.0 and i used keras==2.3.1 several days ago,i can run your programme.but,now i met the question(model_weights() IndexError: list index out of range).i think it is...
> https://zhuanlan.zhihu.com/p/634871699 这里面有 看了一下这个数据集,STS-B数据是text1\ttext2\tlabel形式 > 一架飞机要起飞了。 一架飞机正在起飞。 5 一个男人在吹一支大笛子。 一个人在吹长笛。 3 一个人正把切碎的奶酪撒在比萨饼上。 一个男人正在把切碎的奶酪撒在一块未煮好的比萨饼上。 3 但是训练的代码数据加载是这个样的,跟数据对不太上 ```python def load_sts_data(path): with open(path, 'r', encoding='utf8') as f: return [(line.split("||")[1], line.split("||")[2], line.split("||")[3]) for line...