MMALI3287
Reputation: 19
How to Combine Fine-Tuned Pre-Trained Models on a Custom Dataset in PyTorch?
I have a custom image dataset with 41 classes, and I've fine-tuned this dataset on six pre-trained models:
- ConvNeXt
- DenseNet
- EfficientNet
- RegNet
- ResNet
- Swin Transformers
After fine-tuning, I saved each model as a .pth file.
Now, I want to load these .pth files and combine the models to classify images.
Since the architectures of the pre-trained models are different, I encountered an "unknown keys" error when I tried to load the models. So how do i achieve my goal of combined training?
Upvotes: 0
Views: 34
Answers (0)
Related Questions
- How do I save a trained model in PyTorch?
- Loading pre-trained Transformer model with AddedTokens using from_pretrained
- Fine-tuning a pre-trained LLM for question-answering
- How to load huggingface's BERT after fine-tuning with Pytorch Lightning?
- How to train Pytorch model on custom data
- How to measure the semantic similarities among image features extracted by pre-trained models(e.g. vgg, resnet...)?
- Understanding the Hugging face transformers
- Combine outputs of two Pre Trained models (trained on different dataset) and use some form of binary classifier to predict images