0
$\begingroup$

I am using a ImageNet-trained network to extract features and classify my own images. My images are quite different (microscopic images) from cats and dogs but the features extracted from the ImageNet gave quite promising results by classification.

It would be very easy for me to generate millions of small microscopic images which contain no label. Would it be somehow possible to train my own convolutional neural network? My target images for classification after transfer learning are labeled. Is this somehow possible? Or can I use pseudo labeling (e.g. classes of mean(histogram) or whatever)?

$\endgroup$
0
$\begingroup$

With transfer learning you can re-train the last few layers of your network to learn to classify images on your new dataset. For an example of transfer learning in TensorFlow using VGG16 and Inception architecture, have a look a the following ipython notebook.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.