Get ann ids that satisfy given filter conditions. default skips that filter :param imgIds (int array) : get anns for given imgs

Load anns with the specified ids. :param ids (int array) : integer ids specifying anns :return: anns (object array) : l

Parameters ---------- block (nn.Module): Bottleneck class. - For SENet154: SEBottleneck - For SE-ResN

filtering parameters. default skips that filter. :param catNms (str array) : get cats for given cat names :param supNms (str

Get img ids that satisfy given filter conditions. :param imgIds (int array) : get imgs for given ids :param catIds (int array

Convert annotation which can be polygons, uncompressed RLE to RLE. :return: binary mask (numpy 2D array)

3x3 convolution with padding

Load cats with the specified ids. :param ids (int array) : integer ids specifying cats :return: cats (object array) : l

Load anns with the specified ids. :param ids (int array) : integer ids specifying img :return: imgs (object array) : lo

Dispatch to either CPU or GPU NMS implementations.

Returns the original image object at index in PIL form Note: not using self.__getitem__(), as any transformations passed in could mes

Compute and display summary metrics for evaluation results. Note this functin can *only* be applied on the default parameter setting

Loads COCO bounding-box instance annotations. Crowd instances are handled by marking their overlaps (with all categories) to -1. This

Prepare ._gts and ._dts for evaluation based on params :return: None

return (b, r, g) tuple

Accumulate per image evaluation results and store the result in self.eval :param p: input params for evaluation :return: None

Check whether the arguments available for constructing m2det modules

inject deep into distutils to customize how the dispatch to gcc/nvcc works. If you subclass UnixCCompiler, it's not trivial to get your subcl

Decode locations from predictions using priors to undo the encoding we did for offset regression at train time. Args: loc (tensor): lo

Encode the variances from the priorbox layers into the ground truth boxes we have matched (based on jaccard overlap) with the prior boxes. Arg

Run per image evaluation on given images and store results (a list of dict) in self.evalImgs :return: None

Find a file in a search path

Construct an image path from the image's "index" identifier.

We resize both tensors to [A,B,2] without new malloc: [A,2] -> [A,1,2] -> [A,B,2] [B,2] -> [1,B,2] -> [A,B,2] Then we compute the area of

Compute the jaccard overlap of two sets of boxes. The jaccard overlap is simply the intersection over union of two boxes. Here we operate on

Convert result data from a numpy array [Nx7] where each row contains {imageID,x1,y1,w,h,score,class} :param data (numpy.ndarray)

Load result file and return a result api object. :param resFile (str) : file name of result file :return: res (obj)

Locate the CUDA environment on the system Returns a dict with keys 'home', 'nvcc', 'include', and 'lib64' and values giving the absolute path

Utility function for computing log_sum_exp while determining This will be used to determine unaveraged confidence loss across all examples in

Match each prior box with the ground truth box of the highest jaccard overlap, encode the bounding boxes, then return the matched indices corr

return iou of a and b, numpy version for data augenmentation

Parse a PASCAL VOC xml file

Convert prior_boxes to (xmin, ymin, xmax, ymax) representation for comparison to point form ground truth data. Args: boxes: (tensor)

Returns the original image object at index in PIL form Note: not using self.__getitem__(), as any transformations passed in could mes

Log a scalar variable.