Closed NawelAr closed 4 years ago
which metrics are you using? I seem to face this when I am using F1/fbeta. there are different errors when using roc_auc and accuracy_thresh. Not sure which work best with multiclass vs multilabel. works fine when using only accuracy
which metrics are you using? I seem to face this when I am using F1/fbeta. there are different errors when using roc_auc and accuracy_thresh. Not sure which work best with multiclass vs multilabel. works fine when using only accuracy
I'm using fbeta, and accuracy. Setting multi_label to True fixed it, but I am still confused about it.
which metrics are you using? I seem to face this when I am using F1/fbeta. there are different errors when using roc_auc and accuracy_thresh. Not sure which work best with multiclass vs multilabel. works fine when using only accuracy
Hello, My accuracy is always down to 0. I know it's due to setting multi-label to True. Is there a proper way to do binary classification ?
Set multi-label to false and only use the accuracy metric. Follow the example in the readme.
Set multi-label to false and only use the accuracy metric. Follow the example in the readme.
Thank you, It worked ! Do you know how to get the vector of probabilities after training ? I would like to draw a ROC.
Set multi-label to false and only use the accuracy metric. Follow the example in the readme.
Thank you, It worked ! Do you know how to get the vector of probabilities after training ? I would like to draw a ROC.
Do you have a solution now?
Hello,
I'm working on binary text classification with CamemBert using fast-bert.
When I run the code below
from fast_bert.data_cls import BertDataBunch from fast_bert.learner_cls import BertLearner
databunch = BertDataBunch(DATA_PATH,LABEL_PATH, tokenizer='camembert-base', train_file='train.csv', val_file='val.csv', label_file='labels.csv', text_col='text', label_col='label', batch_size_per_gpu=8, max_seq_length=512, multi_gpu=multi_gpu, multi_label=False, model_type='camembert-base')
learner = BertLearner.from_pretrained_model( databunch, pretrained_path='camembert-base', #'/content/drive/My Drive/model/model_out' metrics=metrics, device=device_cuda, logger=logger, output_dir=OUTPUT_DIR, finetuned_wgts_path=None, #WGTS_PATH warmup_steps=300, multi_gpu=multi_gpu, is_fp16=True, multi_label=False, logging_steps=50)
learner.fit(epochs=10, lr=9e-5, validate=True, schedule_type="warmup_cosine", optimizer_type="adamw") Everything works fine until training. I get this error message when I try to train my model:
RuntimeError Traceback (most recent call last)