Thomas_T

In the file 02-single-view-metrology.pdf, page 8, 1st paragraph, "Finally, let’s suppose that we know that these planes are perpendicular in 3D. In this case, we know that from Equation 12,...

cannot reach the site

1

Cannot reach the site. Any problem?

the relation to DTW

1

could please tell me the relation to soft-DTW project "https://github.com/mblondel/soft-dtw", because I come here from that project? Thanks

Could you please provide the precompiled file, or which boost version should I use to recompile.

import json from PIL import Image import torch from torchvision import transforms from torchviz import make_dot import hiddenlayer as hl from efficientnet_pytorch import EfficientNet model = EfficientNet.from_pretrained('efficientnet-b3') model.eval() hl.build_graph(model, torch.zeros([1,...

How to convert VoxelGrid to 3d numpy array?

1

How to convert VoxelGrid to 3d numpy array? After I get the following grid, how could I get the numpy cube from the grid. mesh = pymesh.load_mesh(args.input_mesh); grid = pymesh.VoxelGrid(args.cell_size,...

I visualize the img2 in max_ssim.py, but it is not the gif shown in the home page. what mistake do I make? The following is the code, modified in max_ssim.py.

1

while ssim_value < 0.95: optimizer.zero_grad() ssim_out = -ssim_loss(img1, img2) ssim_value = - ssim_out.item() print(ssim_value) ssim_out.backward() optimizer.step() ii = np.transpose(img2[0].detach().cpu().numpy(), (1,2,0)) cv2.imshow("pre", ii*255) print(np.max(ii*255)) cv2.waitKey(100)

Could you please release the code for rendering

I install all the package with the recommended version, cuda-11.1, torch=1.8.1, when I run "python train.py --config configs/config_shapenet.yaml", I encounter the following problem. /home/magician/Workspace/anaconda3/envs/conv_onet/bin/python /snap/pycharm-professional/268/plugins/python/helpers/pydev/pydevd.py --multiproc --qt-support=auto --client 127.0.0.1 --port...

The predicted offset by the convolution network is used as the index to interpolate the feature in feature map. Therefore, the gradient cannot back-propagate to the convolution network parameter(Because the...