Receiving "There was a problem during..." Error

[yipy0010]

Hi, I was trying out the steps listed in the README.md. But I realised the main_training.py is in the BIN folder. And if I enter the folder and run it, I get both the "There was a problem during..." error messages. Must I move the scripts out of the BIN folder for the command to work?

[tuncadogan]

Hi, do not cd into the bin folder and do not relocate the scripts please. Instead, run the command as:

python bin/main_training.py ...

This should solve the problem. Als, you should activate your conda environment before running the command.

[yipy0010]

Hi, thanks for the quick reply. I realised it's a problem with using gpu. Apparently, if I comment out the line and force the script to use only CPU, there are no error messages, but when I use gpu, the error messages appear.

I commented out the try and except in main_training.py at lines 143-146. And when I run it with gpu, it gave the following error:
(deepscreen_env) travecta@travecta-desktop:~/Documents/DEEPScreen$ python bin/main_training.py --targetid CHEMBL286 --model CNNModel1 --fc1 256 --fc2 128 --lr 0.01 --bs 64 --dropout 0.25 --epoch 100 --en my_chembl286_training
Namespace(bs=64, dropout=0.25, en='my_chembl286_training', epoch=100, fc1=256, fc2=128, lr=0.01, model='CNNModel1', targetid='CHEMBL286')
Arguments: CHEMBL286-CNNModel1-256-128-0.01-64-0.25-100-my_chembl286_training
GPU is available on this device!
Epoch :0
Training mode: True
Epoch 0 training loss: 23.987353682518005
Traceback (most recent call last):
File "bin/main_training.py", line 67, in
args.dropout, args.epoch, args.en)
File "/home/travecta/Documents/DEEPScreen/bin/train_deepscreen.py", line 144, in train_validation_test_training
training_perf_dict = prec_rec_f1_acc_mcc(all_training_labels, all_training_preds)
File "/home/travecta/Documents/DEEPScreen/bin/evaluation_metrics.py", line 10, in prec_rec_f1_acc_mcc
precision = metrics.precision_score(y_true, y_pred)
File "/home/travecta/anaconda3/envs/deepscreen_env/lib/python3.7/site-packages/sklearn/utils/validation.py", line 73, in inner_f
return f(**kwargs)
File "/home/travecta/anaconda3/envs/deepscreen_env/lib/python3.7/site-packages/sklearn/metrics/_classification.py", line 1623, in precision_score
zero_division=zero_division)
File "/home/travecta/anaconda3/envs/deepscreen_env/lib/python3.7/site-packages/sklearn/utils/validation.py", line 73, in inner_f
return f(**kwargs)
File "/home/travecta/anaconda3/envs/deepscreen_env/lib/python3.7/site-packages/sklearn/metrics/_classification.py", line 1434, in precision_recall_fscore_support
pos_label)
File "/home/travecta/anaconda3/envs/deepscreen_env/lib/python3.7/site-packages/sklearn/metrics/_classification.py", line 1250, in _check_set_wise_labels
y_type, y_true, y_pred = _check_targets(y_true, y_pred)
File "/home/travecta/anaconda3/envs/deepscreen_env/lib/python3.7/site-packages/sklearn/metrics/_classification.py", line 98, in _check_targets
raise ValueError("{0} is not supported".format(y_type))
ValueError: unknown is not supported

[tuncadogan]

Thank you for posting the error we will check it and comment when we have a solution.

[yewmunyip]

Okay, thanks for looking into the matter! In the meantime, I will look into the code and will propose a solution if I found any as well. :)

[tuncadogan]

Thank you very much :)

[yipy0010]

Hi Prof Dogan, I have resolved the error. Please see the attached evaluation_metrics.py. I very much enjoy this work of yours. :)
evaluation_metrics.zip

[tuncadogan]

That is great! thanks! we will examine your changes and apply it if nothing goes wrong