Sample-design-alt

hello,I copy the code in the pycharm,but I found that the weight are 'nan',why?

Great work! Thanks for your sharing. But there are some problems I can't solve. How should I change the fontsize of X-Y axis, and title?

There are some problems when I running python train/disentanglement/dtw/MFCC_dtw.py. 1. Can you tell the function in 132-140? https://github.com/jixinya/EVP/blob/1f725b8e23f5e29f6211d74e3c08636de7053239/train/disentanglement/dtw/MFCC_dtw.py#L132-L140 2. the dimension of mfcc_k is (13, ) is right? The dimension...

About pydw

19

I follow your note, but there are some trouble with me. 1 I can't install pydtw, it It prompts such errors  2 the link of "dtw" file is removed,...

Thanks for your contributions! But i have a question for LVM applied to image classification. How should I use LVM with ICL to predict the labels?

TypeError: MoiraiModule.__init__() missing 7 required positional arguments: 'distr_output', 'd_model', 'num_layers', 'patch_sizes', 'max_seq_len', 'attn_dropout_p', and 'dropout_p'

3

when I perform the code in the https://github.com/SalesforceAIResearch/uni2ts/blob/main/example/moirai_forecast.ipynb, there are some error occur. How should I solve this problem? --------------------------------------------------------------------------- TypeError Traceback (most recent call last) Cell In[5], line 3...

Thanks for you great work! But how should I custom my own dataset in the pretraining stage?

Thanks for your great works! But I have some question about TSC task. 1. Can time series classification really be unsupervised? According to your paper, use embedding and then SVM...

我尝试使用Time-llm在UEA的SRS1 2分类进行尝试，但训练失败了

1

我尝试改写你的代码在分类问题上，但是结果只有50%。这是为什么呢？我也尝试把bf16改为了float32，还有哪些可能存在的问题导致我的模型无法训练？（还有其他几个数据集也存在同样的问题） 这是我的分类forward： ` def classification(self, x_enc): x_enc = self.normalize_layers(x_enc, 'norm') B, T, N = x_enc.size() x_enc = x_enc.permute(0, 2, 1).contiguous().reshape(B * N, T, 1) # 2. 计算统计特征 (保持不变，这些特征对分类也很有用) min_values =...