End-to-End Deep Learning Tutorial (0.0392)

@Mathurin If you put your data in another folder, then you need to modify the code in order to take into account the number of subdirectories in the data path. For example, on Linux, I put the train.csv file in the following folder: DATA_PATH = ‘/home/rick/data/datasciencebowl/Kaggle’ So now to access the file, I write: write_label_csv(“./train-label.csv”, train_frames, get_label_map(os.path.join(DATA_PATH,”train.csv”))) Since there are an additional four subdirectories in the path name, I change the 3 to 7 in the 3rd line of the “def write_label_csv” funtion: index = int(lst[0].split(“/”)[7]) I hope this helps!


Link to Full Article: End-to-End Deep Learning Tutorial (0.0392)