tensorflow-object-contour-detection
tensorflow-object-contour-detection copied to clipboard
Raj-08
A tensorflow implementation of object-contour-detection with fully convolutional encoder decoder network
Hi, does anyone have pre-trained model to share. It can save a lot time for others. Thanks!
Hey guys, I want to know how much time you have cost when run the train.py, and what type of GPU you were using at the same time. Can anybody...
Hi, After running the eval.py file the final predictions are saved as numPy arrays using the code statement: np.save(FLAGS.save_preds+l,P) My question is how should we visualize these predictions in images?...
Hi, Thanks for sharing the code. I am little unsure about the dataset that shoud be used for training. Also, how it should be pre-processed. The paper says that PASCAL...
the article said ‘use the originally annotated contours instead of our refined ones as ground truth for unbiased evaluation’，it means the eval_gt does not use DenseCRF refinement ? like (b),the...
Hi, You code is awesome and really helpful. But I am unable to generate labels. I have downloaded Pascal VOC dataset from this link: http://host.robots.ox.ac.uk/pascal/VOC/voc2012/. I am not able to...
Can anybody share pretrained model? That would be great and would allow others to test the model without prior training.
Hello Raj, You code is awesome and really helpful. But I am unable to generate labels. I have downloaded Pascal VOC dataset from this link: [http://host.robots.ox.ac.uk/pascal/VOC/voc2012/](url). I am not able...
Hi, thanks for sharing the code to your paper. I was wondering if I could change the network to receive only the contours (without classification). As far as I understand...
GT[GT!=255]=0 in create_labels.py practically makes all pixels with value 0 which is weird
