CODEWITHSUNDEEP
deep-learninggpuhardware
Nurjan
Nurjan

Reputation: 6073

Hardware requirements for pre-trained convolutional neural network for image recognition

I know that for training a deep neural network for image recognition a good GPU or GPUs are required since they are more suited for this task than CPUs. It's all clear and there are lots of various tutorials using various libraries on how to do that.

However, when I have trained my deep neural network what are the hardware requirements for running the trained deep neural network for recognizing images in some web application located on a server? Do I steel need powerful GPUs on the server for that? What hardware is more important for running a pre-trained deep neural network - RAM, CPU, storage?

Can I run pre-trained network on Android app for image recognition? Is it a good idea?

Sorry if my questions are too vague and broad, but I couldn't find any proper and detailed comment on this topic.

Upvotes: 0

Views: 1442

Answers (1)

Sashank SV
Sashank SV

Reputation: 50

Ofcourse the answer depends on lot of factors, including the size of your model, number of CNN layers, type of activation functions etc.

But once my model (3 layers of convolution and 256 nodes in full connection) was trained, to make a single image prediction was possible on my regular MacBook Pro (16GB RAM, 2.7 GHz Intel Core i5 processor) with no GPU. The prediction happened instantaneously (< 1sec).

Hope that answers your question.

Upvotes: 1

Related Questions