| Autor: |
Niranjan N. Chiplunkar, J Praveen Gujjar, H R Prasanna Kumar |
| Rok vydání: |
2021 |
| Předmět: |
|
| Zdroj: |
Global Transitions Proceedings. 2:382-385 |
| ISSN: |
2666-285X |
| DOI: |
10.1016/j.gltp.2021.08.068 |
| Popis: |
Transfer learning is used to reuse the pre-trained model. Transfer learning uses the knowledge which was gained from the previous task. Transfer learning is most generally used in image classification, image prediction and natural language processing. Some of the example for the natural language processing it includes sentiment analysis, text auto complete etc. The literature shows that deep learning performance is relatively more when compared with machine learning technique for the large data set. In this paper pre trained models such as MobileNet, MobileNetV2, VGG16, VGG19 and ResNet50 has been used for image classification and prediction. For the image classification and prediction Google Colab notebook has been used. The performance of the system depends on the GPU system hence results are tested in Google colab notebook. The result shows that MobileNetV2 performance is relatively better than other pre trained models. MobileNetV2 uses the less number of parameters as compared with other trained model. ResNet50 accuracy is more when it compared with other trained model with the ImageNet dataset. In the future enhancement transfer learning may be used for natural language processing to obtain highest accuracy. |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
