search

abduallahmohamed / Social-STGCNN

Code for "Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction" CVPR 2020
MIT License
483 stars 141 forks source link

details about dataset .txt file encoding type. #69

Open udita23 opened 11 months ago

udita23 commented 11 months ago

Can you please mention in what format the .txt files are encoded in the current datasets directory. I was trying out with my own custom dataset which I imported from pandas dataframe using both utf-8 and asci encoding. but I received the following error while running the train.sh script File "/home/Social-STGCNN/utils.py", line 122, in init data = read_file(path, delim) File "/home/Social-STGCNN/utils.py", line 79, in read_file for line in f: File "/home/miniconda3/envs/newenv/lib/python3.6/codecs.py", line 321, in decode (result, consumed) = self._buffer_decode(data, self.errors, final) UnicodeDecodeError: 'utf-8' codec can't decode byte 0x80 in position 3131: invalid start byte

AdityaKharmaleGoat7 commented 3 months ago

Great work @abduallahmohamed !!

Could you please explain me about the attribute of the text dataset? Like the significance of the columns in the text file, so that we could also create our own similar dataset.