Finetune Ultrasound 2D Dataset.

IBBM / Cascaded-FCN

Source code for the MICCAI 2016 Paper "Automatic Liver and Lesion Segmentation in CT Using Cascaded Fully Convolutional NeuralNetworks and 3D Conditional Random Fields"

Other

304 stars 127 forks source link

Finetune Ultrasound 2D Dataset. #11

Closed mateovilla2 closed 7 years ago

mateovilla2 commented 7 years ago

Hi,

I would like to train my dataset , which consist of ultrasound 2D images, in gray-scale, for making automatic bone segmentation . I have no GPU, so I would like to finetune your model in order to do the training faster . My images are of different sizes( the height is fixed at 512, but the width varies between 300 and 512. Is there any special consideration in this case ? Your cand find attached an example of an image and the ground truth image_01_0541_croped

Thank you very much,

Cordially,

Mateo Villa

mohamed-ezz commented 7 years ago

Hi @mateovilla2, Regarding the different image size, I think it's fine, but make sure to change cropping parameters accordingly in the training/testing prototxt.

Without a GPU I think training will be way too slow for this large model. If there's no chance to access a GPU, I would try a smaller model. But try it out and see how much time you can afford to wait until training converges.

sqbqamar commented 7 years ago

Hi, Can i get training prototxt of your work..