search

faustomilletari / VNet

GNU General Public License v3.0
287 stars 122 forks source link

how to caculate the receptive field for the deconvolution layers #48

Open caney1989 opened 6 years ago

caney1989 commented 6 years ago

Hi! @faustomilletari , I have read your paper carefully and your excellent work has gave me a lot of help. However, i have some trouble for how to caculate the receptive field for the deconvolution layers. I caculated the receptive field for the networks designd in V-Net by myself , but i can not find the right way to caculate the deconvolution layers. Could you show me some details for this caculation? Thanks very much!!

faustomilletari commented 6 years ago

I have computed it in matconvnet using their tool.

If you look at what happens during deconv you will find the answer.

Regards,

Fausto Milletarì Sent from my iPhone

On 24. Mar 2018, at 09:55, caney1989 notifications@github.com wrote:

Hi! @faustomilletari , I have read your paper carefully and your excellent work has gave me a lot of help. However, i have some trouble for how to caculate the receptive field for the deconvolution layers. I caculated the receptive field for the networks designd in V-Net by myself , but i can not find the right way to caculate the deconvolution layers. Could you show me some details for this caculation? Thanks very much!!

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or mute the thread.

caney1989 commented 6 years ago

Thanks for your reply. Matconvnet using their tool?? Is the tool for the caculation of receptive field based on matconvnet ? Could you show me some details about this tool or give me a web link?？ Thanks very much!!