Bert-Multi-Label-Text-Classification icon indicating copy to clipboard operation
Bert-Multi-Label-Text-Classification copied to clipboard

Expected object of scalar type Bool but got scalar type Byte for argument #2 'other'

Open fx7056 opened this issue 3 years ago • 0 comments

How to fix the problem 02/18/2022 14:31:08 - INFO - root - initializing callbacks 02/18/2022 14:31:08 - INFO - root - ***** Running training ***** 02/18/2022 14:31:08 - INFO - root - Num examples = 127657 02/18/2022 14:31:08 - INFO - root - Num Epochs = 6 02/18/2022 14:31:08 - INFO - root - Total train batch size (w. parallel, distributed & accumulation) = 8 02/18/2022 14:31:08 - INFO - root - Gradient Accumulation steps = 1 02/18/2022 14:31:08 - INFO - root - Total optimization steps = 95748 02/18/2022 14:31:08 - WARNING - root - Warning: There's no GPU available on this machine, training will be performed on CPU. 02/18/2022 14:31:08 - WARNING - root - Warning: The number of GPU's configured to use is 0, but only 0 are available on this machine. 02/18/2022 14:31:08 - INFO - root - Epoch 1/6 Traceback (most recent call last): File "run_bert.py", line 216, in main() File "run_bert.py", line 209, in main run_train(args) File "run_bert.py", line 117, in run_train trainer.train(train_data=train_dataloader, valid_data=valid_dataloader) File "/mnt/c/Users/admin/Downloads/Bert-Multi-Label-Text-Classification-master/pybert/train/trainer.py", line 153, in train train_log = self.train_epoch(train_data) File "/mnt/c/Users/admin/Downloads/Bert-Multi-Label-Text-Classification-master/pybert/train/trainer.py", line 118, in train_epoch self.info[metric.name()] = metric.value() File "/mnt/c/Users/admin/Downloads/Bert-Multi-Label-Text-Classification-master/pybert/train/metrics.py", line 90, in value acc = np.mean(((self.y_pred>self.thresh)==self.y_true.byte()).float().cpu().numpy(), axis=1).sum() RuntimeError: Expected object of scalar type Bool but got scalar type Byte for argument #2 'other'

fx7056 avatar Feb 18 '22 06:02 fx7056