I am using efficient det 512*512. This gave me best results while training the CNN. But problem is this model is heavy, I really need the accuracy. But need to make it ligh weight for some extent. I tried many ways. But still the problem is the same. I tried mathermatically too. Please kindly give me some advices.
Thank you.
Dear Dulashi Karunakalage
These articles might be useful, have a look:
1. https://machinelearningmastery.com/how-to-use-transfer-learning-when-developing-convolutional-neural-network-models/
2. https://machinelearningmastery.com/how-to-improve-performance-with-transfer-learning-for-deep-learning-neural-networks/
3. https://medium.com/starschema-blog/transfer-learning-the-dos-and-donts-165729d66625
4. https://medium.com/starschema-blog/transfer-learning-the-dos-and-donts-165729d66625
5. https://keras.io/guides/transfer_learning/
Kind Regards
Qamar Ul Islam
- Badges
- Science topic
- Similar topics
- Organizational Psychology
- Training