선택한 단어 수는 입니다.
최소 단어 이상 선택하여야 합니다.
최소 단어 이상 선택하여야 합니다.
선택한 단어 수는 30입니다.
최대 10 단어까지만 선택 가능합니다.
최대 10 단어까지만 선택 가능합니다.
제안 방법
- The training starts with both the generator G and discriminator D having a low spatial resolution of 4×4 pixels. As the training advances, successive layers are incrementally added to G and D, thus increasing the spatial resolution of the generated images. This allows stable synthesis in high resolutions and speeds up training considerably.
- The training starts with both the generator G and discriminator D having a low spatial resolution of 4×4 pixels.
- To conclude, in this work we demonstrated a method that uses the generation of synthetic plant disease images for data augmentation to improve performance on various ventures related to agricultural problems with limited data. In the future, we plan to extend our work to additional domains that can benefit from synthesis of this data for improved training and accuracy.
이론/모형
- Our dataset contains images with several diseases and pests in tomato plants but our experiments were mostly carried on the PlantVillage dataset indistinguishable from our dataset in terms of class imbalance and lack of adequate training samples. For the implementation of our GAN architecture we used the TensorFlow framework. All training processes were performed using a setup with an NVIDIA Titan-X 12GB GPU and intel i7 processor.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.