Course Hero Logo

Parameters heatmap tensor input heatmap the gaussian

Course Hero uses AI to attempt to automatically extract content from documents to surface to you and others so you can study better, e.g., in search results, to enrich docs, and more. This preview shows page 514 - 517 out of 544 pages.

Parametersheatmap(Tensor) – Input heatmap, the gaussian kernel will cover on it and maintain themax value.506Chapter 43.mmdet.models
MMDetection, Release 2.25.0center(list[int]) – Coord of gaussian kernel’s center.radius(int) – Radius of gaussian kernel.k(int) – Coefficient of gaussian kernel. Default: 1.ReturnsUpdated heatmap covered by gaussian kernel.Return typeout_heatmap (Tensor)mmdet.models.utils.get_uncertain_point_coords_with_randomness(mask_pred,labels,num_points,oversample_ratio,importance_sample_ratio)Getnum_pointsmost uncertain points with random points during train.Sample points in [0, 1] x [0, 1] coordinate space based on their uncertainty. The uncertainties are calculated foreach point using ‘get_uncertainty()’ function that takes point’s logit prediction as input.Parametersmask_pred(Tensor)Atensorofshape(num_rois,num_classes,mask_height,mask_width) for class-specific or class-agnostic prediction.labels(list) – The ground truth class for each instance.num_points(int) – The number of points to sample.oversample_ratio(int) – Oversampling parameter.importance_sample_ratio(float) – Ratio of points that are sampled via importnacesampling.ReturnsA tensor of shape (num_rois, num_points, 2)that contains the coordinates sampled points.Return typepoint_coords (Tensor)mmdet.models.utils.get_uncertainty(mask_pred,labels)Estimate uncertainty based on pred logits.We estimate uncertainty as L1 distance between 0.0 and the logits prediction in ‘mask_pred’ for the foregroundclass inclasses.Parametersmask_pred(Tensor)maskpredicationlogits,shape(num_rois,num_classes,mask_height, mask_width).labels(list[Tensor]) – Either predicted or ground truth label for each predicted mask,of length num_rois.ReturnsUncertainty scores with the most uncertainlocations having the highest uncertainty score,shape (num_rois, 1, mask_height, mask_width)Return typescores (Tensor)mmdet.models.utils.interpolate_as(source,target,mode= bilinear,align_corners=False)Interpolate thesourceto the shape of thetarget.Thesourcemust be a Tensor, but thetargetcan be a Tensor or a np.ndarray with the shape (..., target_h, target_w).Parameterssource(Tensor) – A 3D/4D Tensor with the shape (N, H, W) or (N, C, H, W).43.7.utils507
MMDetection, Release 2.25.0target(Tensor | np.ndarray) – The interpolation target with the shape (..., target_h,target_w).mode(str) – Algorithm used for interpolation.The options are the same as those inF.interpolate(). Default:'bilinear'.align_corners(bool) – The same as the argument in F.interpolate().ReturnsThe interpolated source Tensor.Return typeTensormmdet.models.utils.make_divisible(value,divisor,min_value=None,min_ratio=0.9)Make divisible function.This function rounds the channel number to the nearest value that can be divisible by the divisor. It is taken fromthe original tf repo. It ensures that all layers have a channel number that is divisible by divisor. It can be seenhere:# noqaParametersvalue(int) – The original channel number.

Upload your study docs or become a

Course Hero member to access this document

Upload your study docs or become a

Course Hero member to access this document

End of preview. Want to read all 544 pages?

Upload your study docs or become a

Course Hero member to access this document

Term
Spring
Professor
N/A
Tags
Test, Graphics processing unit, MMDetection

Newly uploaded documents

Show More

  • Left Quote Icon

    Student Picture

  • Left Quote Icon

    Student Picture

  • Left Quote Icon

    Student Picture