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

1x1 convolution

3x3 convolution with padding

pull uniform random sample(s) from [a,b)

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

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

Apply non-maximum suppression at test time to avoid detecting too many overlapping bounding boxes for a given object. Args: boxes: (te

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

proxy to torch.rand(n)[0]

:param in_channels: :param inter_channels: :param dimension: :param sub_sample: :param bn_layer:

Convert prior_boxes to (cx, cy, w, h) representation for comparison to center-size form ground truth data. Args: boxes: (tensor) poin

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

:param x: (b, c, t, h, w) :param return_nl_map: if True return z, nl_map, else only return z. :return:

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

r"""ResNet-101 model from `"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>`_ Args: pretrained (

r"""ResNet-152 model from `"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>`_ Args: pretrained (

r"""ResNet-18 model from `"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>`_ Args: pretrained (b

r"""ResNet-34 model from `"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>`_ Args: pretrained (b

r"""ResNet-50 model from `"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.pdf>`_ Args: pretrained (b

r"""ResNeXt-101 32x8d model from `"Aggregated Residual Transformation for Deep Neural Networks" <https://arxiv.org/pdf/1611.05431.pdf>`_ Args

r"""ResNeXt-50 32x4d model from `"Aggregated Residual Transformation for Deep Neural Networks" <https://arxiv.org/pdf/1611.05431.pdf>`_ Args:

torch implementation of np.random.choice(), x1.1~1.5 slower than original function