tag:blogger.com,1999:blog-1106783043299925876.post5451241934711235268..comments2024-03-02T13:01:32.864+05:30Comments on Codes of Interest | Deep Learning Made Fun: image_data_format vs. image_dim_ordering in Keras v2Thimira Amaratungahttp://www.blogger.com/profile/13330876639489088914noreply@blogger.comBlogger1125tag:blogger.com,1999:blog-1106783043299925876.post-20912776902557466582018-04-17T04:05:18.182+05:302018-04-17T04:05:18.182+05:30Thank you for your post. If I have a dataset which...Thank you for your post. If I have a dataset which is prepared for theano, the shape of training data will be (samples, channels, rows, cols) just like you mentioned. If I changed the backend from theano to tensoflow, do I need to change my training data's shape to (samples, rows, cols, channels) before loading into my program, then do the others? or load the training date first, then reshape to (samples, rows, cols, channels), then do the others? Xu Zhanghttps://www.blogger.com/profile/12211764606336992270noreply@blogger.com