There are several ways to reduce the training time of CNN. At first you need to know about the configuration of your computer. Do you have GPU. You can add it with your computer. If you have that GPU, then concentrate on your feature maps. I think you have chosen your feature maps more than u need, most of the designer do this wrong. If you still facing same problem we can discuss again..
There are several ways to reduce the training time of CNN. At first you need to know about the configuration of your computer. Do you have GPU. You can add it with your computer. If you have that GPU, then concentrate on your feature maps. I think you have chosen your feature maps more than u need, most of the designer do this wrong. If you still facing same problem we can discuss again..
You have three parameters that must adjust in order to have less time during the training phase:
The size of the images or the input data.
The number of layers (convolutional layers and max-pooling layers) of CNN.
The use of GPUs instead of CPUs in the calculations.
You can also use a web service for the training your model ( https://www.youtube.com/watch?v=Bgwujw-yom8 )
Another technique to minimize the time with CNN is to use Transfer Learning. Therefore, instead of building and training a CNN from, we’ll use a pre-built and pre-trained model applying transfer learning.