[help wanted] cannot run the train.py successfully

[DFTandQC]

I hope you can help solve the problem. I use anaconda for the creation of a virtual environment and run train.py in spyder with python 3.11. When I run the train.py, there shows up the error. The dataset used by this code is sn2_reactions.npz, which is got from: https://zenodo.org/record/2605341. Other files and parameters are not verified.

THe error report:

File D:\programs\anaconda3\Lib\site-packages\spyder_kernels\py3compat.py:356 in compat_exec
exec(code, globals, locals)

File d:\programs\qml\copies\physnet-master\physnet-master\train.py:122
Eshift=data_provider.EperA_mean,

File D:\programs\qml\copies\PhysNet-master\PhysNet-master\training\DataProvider.py:106 in EperA_mean
self._compute_E_statistics()

File D:\programs\qml\copies\PhysNet-master\PhysNet-master\training\DataProvider.py:95 in _compute_E_statistics
tmp = self.get_data(self.idx_train[i])

File D:\programs\qml\copies\PhysNet-master\PhysNet-master\training\DataProvider.py:196 in get_data
return self.data[idx]

File D:\programs\qml\copies\PhysNet-master\PhysNet-master\training\DataContainer.py:147 in getitem
for k, i in enumerate(idx):

TypeError: 'numpy.int32' object is not iterable

Desktop
OS: [Windows11]
Anaconda version：conda 23.7.3
Python Version: [3.11.4]
Package Version: [tensorflow 2.13.0], [numpy 1.24.3]

[LIVazquezS]

Hi,

Please consider doing your training with a version of Tensorflow 1. As the differences between TF1 and TF2 are very large, it is possible that you need to make changes to the code to adapt it.

For this particular problem, I think you need to run the file as:

python train.py @config.txt

It might be that it is not reading the number of training samples and then you receive an error.

Cheers,

L

[ShawnBox]

Hi,

I met the same problem with @DFTandQC . However, my python version is [3.6.3] and tensorflow version is [1.10.0]. And the solution of @LIVazquezS did not work.

After checking the code, I think the problem is caused by file [/training/DataCotainer.py] line 128
if type(idx) is int or type(idx) is np.int64:

I edit it like
if type(idx) is int or type(idx) is np.int64 or type(idx) is np.int32:

Then the problem is solved.