All Questions
Tagged with fine-tuning transfer-learning
8
questions
1
vote
0
answers
42
views
MusicVAE fine-tune pre-trained model?
Is there a way to start training MusicVAE from existing pre-trained models from Magenta?
https://magenta.tensorflow.org/music-vae
https://github.com/magenta/magenta/tree/main/magenta/models/music_vae#...
0
votes
0
answers
14
views
FineTuning Resnet50 for a binary classification problem and I got different validation accuracy using classification_report and model.evaluate
I'm working on a binary classification problem using the pre-trained model Resnet50, I got a good result on training and validation accuracy using model.evaluate
Training Data :
loss: 0.0271
accuracy: ...
- 11
1
vote
1
answer
969
views
How to fine-tune gpt2 with a custom set of unlabelled document
I'm newbie to GPT2 fine-tuning. My goal is to fine-tune GPT-2 (or BERT) on a my own set of document, in order to be able to query the bot on a topic contained in these documents, and receive an answer....
- 11
0
votes
1
answer
982
views
Fine tuning freezing weights nnUNet
Good morning,
I've followed the instructions in this github issue:
https://github.com/MIC-DKFZ/nnUNet/issues/1108
to fine-tune an nnUNet model (pyTorch) on a pre-trained one, but this method retrain ...
- 3
0
votes
1
answer
997
views
How to improve an accuracy of validation and test of my model of Transfer Learning BERT
I trained my BERT model, then I get 99% in the training part whoever in part of validation I get just 80%, so how can I improve my validation accuracy?
Code :
def build_model(self, n_categories):
...
- 81
0
votes
1
answer
785
views
Huggingface - Finetuning in Tensorflow with custom datasets
I have been battling with my own implementation on my dataset with a different transformer model than the tutorial, and I have been getting this error AttributeError: 'NoneType' object has no ...
- 361
1
vote
0
answers
271
views
Proper use of BatchNormalization when Fine-Tunning
I`m using keras and TF 2.0
I'm trying to implement ResNet50 pre-trained on ImageNet to a different problem (pneumonia binary classification) and I've found that there is some discussion online about ...
0
votes
1
answer
1k
views
Fine-tuning with a very low learning rate. Any sign that something is not good?
I have working with deep reinforcement learning and in the literature, usually the learning rates are lower than I found in other settings.
My model is the following one:
def create_model(self):
...
- 89