ifp-uiuc / do-neural-networks-learn-faus-iccvw-2015 Goto Github PK

Nice work Man.
please tell me the solution of this error
Traceback (most recent call last):
File "D:/Masters/Research/dexpression-master/Ck_to_npy.py", line 450, in
condenser = CKPlusCondenser(input_path, save_path)
File "D:/Masters/Research/dexpression-master/Ck_to_npy.py", line 22, in init
shutil.copytree(original_dataset_path, condensed_dataset_path)
File "C:\Users\nomi\Anaconda3\lib\shutil.py", line 320, in copytree
srcname = os.path.join(src, name)
File "C:\Users\nomi\Anaconda3\lib\ntpath.py", line 76, in join
path = os.fspath(path)
TypeError: expected str, bytes or os.PathLike object, not NoneType

Thankss in advance

Has anyone tried this code before? I run the code, the accuracy is just about 50%, lower than the paper mentioned (around 96%). Could any one tell me why?

I am trying to run the data script for CK+ dataset with python 2

python make_ck_plus_dataset.py --input_path "E:\CK+" --save_path E:\approach1_april_10\data

It gives the following error:

Traceback (most recent call last):
File "make_ck_plus_dataset.py", line 459, in
numpy_file_generator.run()
File "make_ck_plus_dataset.py", line 298, in run
num_samples)
File "make_ck_plus_dataset.py", line 332, in make_data_label_mats
y[index_slice] = label_vec
ValueError: could not broadcast input array from shape (4) into shape (3)

What am I doing wrong?