Questions tagged [pretraining]

The tag has no usage guidance.

Filter by
Sorted by
Tagged with
0 votes
0 answers
3 views

Is it possible to "fine-tune" a pre-trained logistic regression model?

Fine tuning is a concept commonly used in deep learning. We may have a pre-trained model and then fine-tune it to our specific task. Does that apply to simple models, such as logistic regression? For ...
user avatar
1 vote
1 answer
21 views

Pretrained vs. finetuned model

I have a doubt regarding terminology. When dealing with huggingface transformer models, I often read about "using pretrained models for classification" vs. "fine-tuning a pretrained ...
user avatar
  • 257
2 votes
0 answers
42 views

how to improve recall by retraining a model on its feedback

I am creating a supervised model using sensitive and scarce data. For the sake of discussion, I've simiplified the problem statement by assuming that I'm creating a model for identifying dogs. Let's ...
user avatar
0 votes
0 answers
18 views

Baseline model and transfer learning

I've tried to find any guidance on using transfer learning when building baseline models for ML projects (CNN in my case) but found no clues on good practices in the matter. My logic says that no ...
user avatar
0 votes
1 answer
27 views

Can I leave natural outliers in a dataset in training?

Can I leave unedited natural outliers in a dataset (outliers that have not appeared just because of mistyping of mistakes in the data)? Or should I also remove them or change them?
user avatar
  • 33
1 vote
1 answer
47 views

test data is not a good representation of train data

I have predefined train and test sets. On generating some statistics like value_counts and checking the unique values, I feel that there is a 'lot' of difference between the distributions of the ...
user avatar
0 votes
0 answers
31 views

How long does it take to fine-tune XLNet?

XLNet takes a lot more time than BERT during pre-training. This results in XLNet performing better than BERT in over 20 NLP tasks. How long does XLNet take for fine-tuning (let's assume this is ...
user avatar
0 votes
0 answers
14 views

Using mathematical derivatives of input data to augment training input data

I'm thinking of how to design a basic feedforward neural network that would be able to predict future datapoints given past datapoints. I'm very new to neural network design so I'm wondering if there'...
user avatar
  • 9
0 votes
0 answers
46 views

One single-batch training on Huggingface Bert model "ruins" the model

For some reason, I need to do further (2nd-stage) pre-training on Huggingface Bert model, and I find my training outcome is very bad. After debugging for hours, surprisingly, I find even training one ...
user avatar
  • 101
2 votes
1 answer
593 views

Fine-tuning pre-trained Word2Vec model with Gensim 4.0

With Gensim < 4.0, we can retrain a word2vec model using the following code: ...
user avatar
  • 51
1 vote
0 answers
16 views

Working on an image classification project (microscopic images) , have some doubts [closed]

Currently, I am working on an image classification project. The data set contains very high resolution images taken via an electron microscope. Hence, I have few and limited instances. I have done EDA ...
user avatar
  • 11
0 votes
0 answers
68 views

Does NSP task corrupt context during pre-training?

During the pre-training of BERT, if we just use MLM our input will be: [CLS] SentenceA [SEP]. So if there is a masked token in Sentence A, it will be predicted by ...
user avatar
  • 101
1 vote
1 answer
49 views

What the differences between self-supervised/semi-supervised in NLP?

GPT-1 mentions both Semi-supervised learning and Unsupervised pre-training but it seems like the same to me. Moreoever, "Semi-supervised Sequence Learning" of Dai and Le also more like self-...
user avatar
0 votes
1 answer
23 views

What is the common practice for NLP or text mining for non-English?

A lot of natural language processing tools are pre-trained with corpus in English. What if ones need to analyze, say, Dutch text? The blogs I find online are mostly saying traslating text into English ...
user avatar
0 votes
1 answer
130 views

Where to get models with weights instead of only weights? What's the purpose of .h5 files?

I have downloaded .h5 files from qubvel/resnet and qubvel/efficientnet. I was trying to use some models as a backbone for my model but I'm getting the following ...
user avatar
  • 103
1 vote
2 answers
297 views

Would there be any reason to pretrain BERT on specific texts?

So the official BERT English model is trained on Wikipedia and BookCurpos (source). Now, for example, let's say I want to use BERT for Movies tag recommendation. Is there any reason for me to pretrain ...
user avatar
0 votes
1 answer
227 views

How to access GPT-3, BERT or alike?

I am interested in accessing NLP models mentioned in scientific papers, to replicate some results and experiment. But I only see waiting lists https://openai.com/blog/openai-api/ and licenses granted ...
user avatar
0 votes
2 answers
50 views

Logic behind pre-trained weights and transfer learning

I am not sure about the logic behind, how pre-trained weights actually make sense and translate into a new problem. To be more specific; for example in a object detection network, how would a model's ...
user avatar
  • 1
1 vote
2 answers
629 views

Does finetuning BERT involving updating all of the parameters or just the final classification layer?

Currently learning and reading about transformer models, I get that during the pretraining stage the BERT model is trained on a large corpus via MLM and NSP. But during finetuning, for example trying ...
user avatar
  • 11
1 vote
2 answers
2k views

Deploying multiple pre-trained model (tar.gz files) on Sagemaker in a single endpoint

We have followed the following steps: Trained 5 TensorFlow models in local machine using 5 different training sets. Saved those in .h5 format. Converted those into tar.gz (Model1.tar.gz,...Model5.tar....
user avatar
3 votes
1 answer
53 views

Are there any objections to using the same (unlabelled) data for pre-training of a BERT-Based model and the downstream task?

I'm looking to train an Electra model using unlabelled data in a specific field. Are there any objections to using the same data for unsupervised learning and then using the same data downstream for ...
user avatar
1 vote
2 answers
249 views

Semantic segmentation with greyscale images

I'm trying to reproduce a research with greyscale images instead of colour images. I have found that there are pre-trained networks, like VGG16, with ImageNet. But that dataset has colour images, and ...
user avatar
0 votes
1 answer
17 views

Question of pretraining text-generation task, it seems that pretraining is not work for a small model?

My task is to generate keywords from sentences. I pretrain a text-generation model. I mask the sentences' tokens and predict the whole sentences' tokens. Pretraining batch_size = 8 and step = 1000000 ...
user avatar
  • 561