![]() ![]() Output = UpSampling2D(size = (factor**4,factor**4),interpolation='bilinear')(output) Output = UpSampling2D(size = (factor**3,factor**3),interpolation='bilinear')(output) Output = UpSampling2D(size = (factor**2,factor**2),interpolation='bilinear')(output) Output = tf.convert_to_tensor(output,np.float32) Here is the code: def gethypercols(model,image): ![]() What could be the potential problem behind this and are there any other ways to convert a tensor to numpy array. I am using a generator to load the image one by one to the input of model but still after running for 120 tensors, it is giving me out of memory error. I am using () to convert the output tensor of hypercolumns model generated from a image classification network to numpy array and it is running fine for a few tensors (like 120 tensors). ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |