inpainting_gmcnn
inpainting_gmcnn copied to clipboard
shepnerd
Image Inpainting via Generative Multi-column Convolutional Neural Networks, NeurIPS2018
 As shown in the picture above, the error is not updated and changes randomly. I'd appreciate it if you could tell me the solution.
File "/Users/xxxxxx/opt/anaconda3/envs/gmcnn/lib/python3.6/site-packages/numpy/core/fromnumeric.py", line 52, in _wrapfunc return getattr(obj, method)(*args, **kwds) AttributeError: 'list' object has no attribute 'argmax'
Does anyone know the format of the data file with all of the paths when training your own images? I can't figure it out. I tried a .flist file tat...
Hello, I found a performance issue in the definition of `free_form_mask_tf,` tensorflow/net/ops.py, [tf.py_func and tf.reshape](https://github.com/shepnerd/inpainting_gmcnn/blob/ba7f7109c38c3805800283cdb9d79cd7c4a3294f/tensorflow/net/ops.py#L56) will be created repeatedly during program execution, resulting in reduced efficiency. I think `p` should...
When I was running the train.py , this error occurred: self.conv7 = partial(tf.layers.conv2d, kernel_size=7, activation=tf.nn.elu, padding='SAME') AttributeError: module 'tensorflow' has no attribute 'layers' and I could not find the solution,please...
tensorflow.python.framework.errors_impl.ResourceExhaustedError: OOM when allocating tensor with shape[4096,128,4,4] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc [[Node: inpaint_net/b1conv10_atrous/Conv2D = Conv2D[T=DT_FLOAT, data_format="NHWC", dilations=[1, 1, 1, 1], padding="VALID", strides=[1, 1, 1, 1], use_cudnn_on_gpu=true,...
Hi, I hope you still give support for this repository. I tried converting this repository model to Tensorflow 2x step by step. I think everything was fine, but when training...
hi，I am a newer of image inpainting, i want to known why use the layer 'ConfidenceDrivenMaskLayer' ? where can i find some docs or explain for that?
