suke27
suke27
Hi, thanks for your great work, i have a question for style transfer, currently i found the style transfer result is related to train patch size, for example if i...
I found you are reload model for different shape input images, that make inference process too slow. also it is too slow when test first time. is there any one...
fast style transfer solution also can apply for SR, does anybody know how to training for SR. for fast style transfer network, input and output has same shape, should I...
Hi, I am not familiar with tensorflow, seems I can not do finetune with pretrained model my code like below: import tensorflow as tf sess = tf.Session() new_saver = tf.train.import_meta_graph('my_test_model.meta')...
Hi, i have a question for style transfer. currently style transfer almost use BN/IN and gram matrix in train process, my question is that, is there any solution which use...
I found default transfer parameter is cmd:option('-content_weight', 1) cmd:option('-style_weight', 1) cmd:option('-tv_weight', 0, 'Total variation weight.') seems not same with common option(Gatys set 1000:1), is it your pretrained option? and do...
could you help to check how do we test different brush art style transfer using your code? thank you!
Hello, do you use REDS as training dataset?
Hello, thank you for your great jobs. i have a question, what is frozen_inference_graph.pb from. i found it's size is different with 2 checkpoint files.
Hi, i have a question about pretrained model, which dataset is using for pretrained model. for example deeplabv3-mobilenetv2 one more question: when i download pretrained model and unzip it with...