generative_inpainting
generative_inpainting copied to clipboard
DeepFill v1/v2 with Contextual Attention and Gated Convolution, CVPR 2018, and ICCV 2019 Oral
Do I need to train the model with mask binary map and ground truth

Hi, Congratulations for your outstanding papers, they contain several innovations and contributions. I am conducting research on face de-occlusion and inpainting, and came across your papers. The research requires the...
Hello, I have this error during the test. How can I solve it? Process finished with exit code -1073741819 (0xC0000005)
When I train it on my own dataset, it paused on this step without feedback over a day as the pic shows. I wonder if this is normal. Maybe what...
hello, how to get optical flow picture?Looking forward to your reply
Hi, @JiahuiYu I modified your network structure, and train it. Also, this is my first time to build a model for image inpainting. So during training time, I have no...
I'm trying to convert this model to a tensorflow.js format so I can perform in-browser client-side inference of the model. To do this, the model needs to be in the...
Hi, I want to test pretrained celeba model. I run the code in Ubuntu. When I wrote test code in terminal, model loaded succesfully. But I want to test many...
when I'm trying to set " num_gpus_per_job: 2 " in inpaint.yml and rewrite something in the train.py: discriminator_training_callback = ng.callbacks.SecondaryMultiGPUTrainer( num_gpus=FLAGS.num_gpus_per_job, pstep=1, optimizer=d_optimizer, var_list=d_vars, max_iters=1, grads_summary=False, graph_def=multigpu_graph_def, graph_def_kwargs={ 'model': model,...