Echo-Ji / ST-SSL

ST-SSL (STSSL): Spatio-Temporal Self-Supervised Learning for Traffic Flow Forecasting/Prediction
152 stars 29 forks source link

can't load other datasets in ST-SSL_Dataset #1

Closed shiyuqiii closed 6 days ago

shiyuqiii commented 1 year ago

I download all datasets from ST-SSL_Dataset. when I load BJTaxi in ST-SSL_Dataset: Failed to interpret file '../ST-SSL_Dataset/NYCBike1/test.npz' as a pickle.

my numpy version is 1.23.3

XBR-1111 commented 1 year ago

I would like to share that I successfully loaded BJTaxi test data using the following code. It worked for me. Additionally, I would like to mention that my numpy version is 1.23.1.

import numpy as np

data = np.load('./BJTaxi/test.npz')
for file in data.files:
    print(file, data[file].shape)

If you could share any specific error messages or log files related to the issue, it would greatly help in identifying the problem.

DataScience-SX commented 10 months ago

can't load other datasets in ST-SSL_Dataset with numpy 1.22.0.

and the error is as follows: Traceback (most recent call last): File "e:/x/xx/ST-SSL/npz.py", line 3, in data = np.load('E:/x/xx/ST-SSL/data/BJTaxi/test.npz') File "D:\anaconda3\envs\ptgpu\lib\site-packages\numpy\lib\npyio.py", line 435, in load raise ValueError("Cannot load file containing pickled data " ValueError: Cannot load file containing pickled data when allow_pickle=False

If I add"allow_pickle=True",it alse had error: data = np.load('E:/x/xx/ST-SSL/data/BJTaxi/test.npz', allow_pickle=True) File "D:\anaconda3\envs\ptgpu\lib\site-packages\numpy\lib\npyio.py", line 440, in load raise pickle.UnpicklingError( _pickle.UnpicklingError: Failed to interpret file 'E:/x/xx/ST-SSL/data/BJTaxi/test.npz' as a pickle

Echo-Ji commented 8 months ago

can't load other datasets in ST-SSL_Dataset with numpy 1.22.0.

and the error is as follows:

Traceback (most recent call last): File "e:/x/xx/ST-SSL/npz.py", line 3, in data = np.load('E:/x/xx/ST-SSL/data/BJTaxi/test.npz') File "D:\anaconda3\envs\ptgpu\lib\site-packages\numpy\lib\npyio.py", line 435, in load raise ValueError("Cannot load file containing pickled data " ValueError: Cannot load file containing pickled data when allow_pickle=False If I add"allow_pickle=True",it alse had error: data = np.load('E:/x/xx/ST-SSL/data/BJTaxi/test.npz', allow_pickle=True) File "D:\anaconda3\envs\ptgpu\lib\site-packages\numpy\lib\npyio.py", line 440, in load raise pickle.UnpicklingError( _pickle.UnpicklingError: Failed to interpret file 'E:/x/xx/ST-SSL/data/BJTaxi/test.npz' as a pickle

How do you download the data?

If you download from ST-SSL_Dataset, please ensure you use the lfs tool.

Specifically, you have to get these data files pulled using git-lfs.

git lfs install
git lfs pull

Otherwise, the .npy file will be corrupted, so you cannot open them.

Echo-Ji commented 8 months ago

I download all datasets from ST-SSL_Dataset. when I load BJTaxi in ST-SSL_Dataset: Failed to interpret file '../ST-SSL_Dataset/NYCBike1/test.npz' as a pickle.

my numpy version is 1.23.3

You'd better get these data files pulled using git-lfs.

git lfs install
git lfs pull

Otherwise, the .npy file will be corrupted, so you cannot open them.