tag:blogger.com,1999:blog-1106783043299925876.post5880160792062596762..comments2024-03-02T13:01:32.864+05:30Comments on Codes of Interest | Deep Learning Made Fun: What is the image_dim_ordering parameter in Keras, and why is it importantThimira Amaratungahttp://www.blogger.com/profile/13330876639489088914noreply@blogger.comBlogger3125tag:blogger.com,1999:blog-1106783043299925876.post-40745718208306084482018-11-09T22:08:22.640+05:302018-11-09T22:08:22.640+05:30Nice!!
Nice!!<br />Anonymoushttps://www.blogger.com/profile/11140924345955669415noreply@blogger.comtag:blogger.com,1999:blog-1106783043299925876.post-39910476792871975862017-09-01T15:00:46.607+05:302017-09-01T15:00:46.607+05:30Yes, you're right. It sounds confusing.
I have...Yes, you're right. It sounds confusing.<br />I have now updated it to (hopefully) make it clear.<br /><br />Thanks,Thimira Amaratungahttps://www.blogger.com/profile/13330876639489088914noreply@blogger.comtag:blogger.com,1999:blog-1106783043299925876.post-41786366780867858402017-07-20T02:50:21.881+05:302017-07-20T02:50:21.881+05:30"TensorFlow expects the 'channels' di..."TensorFlow expects the 'channels' dimension to be at index 4 of the tensor – i.e. tensor with shape (samples, rows, cols, channels) – Theano will expect 'channels' at index 1 – i.e. tensor with shape (samples, channels, rows, cols)"<br /><br />At the risk of sounding pedantic, it seems to me that you're using two different indexing techniques (base 1 and base 0). I believe you mean to say one of the following:<br /><br />a) TF uses index 4, and Theano uses index 2<br />b) TF uses index 3, and Theano uses index 1Anonymoushttps://www.blogger.com/profile/06781410818786951621noreply@blogger.com