Open leekwunfung817 opened 2 years ago
You can comment out the load weight codes to train a new model. I tried this... after 80 epochs, the result is still not good. With a trained model, I can easily get a good model within 40 epochs.
You can comment out the load weight codes to train a new model. I tried this... after 80 epochs, the result is still not good. With a trained model, I can easily get a good model within 40 epochs.
I want to inference new objects which totally do not exist in the trained model, did you train with the same set of objects?
You can comment out the load weight codes to train a new model. I tried this... after 80 epochs, the result is still not good. With a trained model, I can easily get a good model within 40 epochs.
I want to inference new objects which totally do not exist in the trained model, did you train with the same set of objects?
I used my own dataset. But I only have about 300 images.
You can comment out the load weight codes to train a new model. I tried this... after 80 epochs, the result is still not good. With a trained model, I can easily get a good model within 40 epochs.
I want to inference new objects which totally do not exist in the trained model, did you train with the same set of objects?
I used my own dataset. But I only have about 300 images.
Do those data contain the previous existing classes in the trained model?
@leekwunfung817
A good deep learning training uses thousands of images to learn its characteristics. Therefore, the pre-trained model has already learned many features, such as: borders, textures, colors, among others. So when you train your model in the last layers you won't need thousands of images. Hundreds of images will be enough.
You can comment out the load weight codes to train a new model. I tried this... after 80 epochs, the result is still not good. With a trained model, I can easily get a good model within 40 epochs.
I want to inference new objects which totally do not exist in the trained model, did you train with the same set of objects?
I used my own dataset. But I only have about 300 images.
Do those data contain the previous existing classes in the trained model?
Not at all
Why do all the tutorials of model training will use trained models? Theoretically, it will be affected by previous training data to cause it to be less accurate.
1: How could I train a model without using a trained model? 2: Why not many people ask to train a pure new model for more accuracy? 3: Is that better?