0

I'm using the latest version of ML.NET image classification in Visual Studio 2019 on a Windows 10 PC to detect inappropriate images. I was using a dataset of 3000 SFW and 3000 NSFW images to train it, but it got stuck while training. There are no errors outputted, it just stops using the CPU and stops outputting to the console.

It has often stopped randomly after a line such as:

[Source=ImageClassificationTrainer; ImageClassificationTrainer, Kind=Trace] Phase: Bottleneck Computation, Dataset used: Train, Image Index: 1109

or

[Source=ImageClassificationTrainer; MultiClassClassifierScore; Cursor, Kind=Trace] Channel disposed

After it stops using the CPU the training page on the machine learning model builder remains the same:

enter image description here

I have also tried this with a smaller dataset of 700 images for each type but ended up with similar results. What's causing this?

Community
  • 1
  • 1
230Daniel
  • 432
  • 3
  • 16

1 Answers1

0

This may be related to the chosen learning environment. Most likely you chose GPU training, but it is not supported. Choose CPU.

Easytrading
  • 16
  • 1
  • Hi, thanks for your answer! I've since moved on from this project so won't be able to see if your fix solved the problem. If anybody else had this issue and this solved it, please let me know so I can mark this as the solution! – 230Daniel Oct 27 '20 at 11:32
  • Yes, I ran the machine learning on a machine with a video card that supports CUDA and the problem disappeared. – Easytrading Oct 28 '20 at 12:03