TFC-pretraining
TFC-pretraining copied to clipboard
mims-harvard
Self-supervised contrastive learning for time series via time-frequency consistency
There seems to be an issue with the Gesture Dataset, having repetitive channels. The below shows the training dataset.
In the paper, you mentioned using ResNet, but there is a Transformer in the code. The built-in implementation of Pytorch is still used, where the input is supposed to be...
It's noted that the code reports the accuracy for each epoch and also selects the highest accuracy. I wonder if the results reported in the paper are the ones selected...
could you release the baseline method code TNC, CPC etc.
backbone
thank you for your time series work. for transformer backbone, my SleepEEG2Epilepsy reproduce result is close to paper，but others i can't get a good result. I refered to the paper...
Thank you for you sharing. But I can't figure out what the "data_pre_processing" is when i try to run the code of simclr. Could you please give the solution?
Hello. **DESCRIBE THE BUG** I'm trying to reproduce the results of the paper and I've downloaded the datasets using the `download_datasets.sh` script and preprocessed them usig the `process_datasets.sh` script. However,...
When I run `run_experiments.py` for training, I encounter a `FileNotFoundError: [Errno 2] No such file or directory: "TFC-pretraining-main/code/baselines/CLOCS/results/CMSC/sleepEDF/leads_['I']/embedding_320/seed4/pretrained_weight"`. I'm unsure where the issue arises. Could you please provide the pre-trained...
I have a problem. When I get one_hot_encode for my fine 275 line, Should I write **onehot_label = F.one_hot(labels,config.num_classes_target)** instead of **onehot_label = F.one_hot(labels)**
I noticed that the Time-Frequency Consistency Loss is not being utilized in your code. Could you please confirm whether this is intentional or not? And if it is not being...
Metadata
Owner
Metadata
Self-supervised contrastive learning for time series via time-frequency consistency