Add a conv2d / batchnorm / leaky ReLU block. Args: in_ch (int): number of input channels of the convolution layer. out_ch

Efficient version of torch.cat that avoids a copy if there is only a single element in a list

Concatenates a list of BoxList (having the same image size) into a single BoxList Arguments: bboxes (list[BoxList])

Args: num_channels: conv_channels: first_time: whether the input comes directly from the efficientn

Compute the intersection over union of two set of boxes. The box order must be (xmin, ymin, xmax, ymax). Arguments: box1: (BoxList)

1x1 convolution

Helper function to synchronize (barrier) among all processes when using distributed training

Run all_gather on arbitrary picklable data (not necessarily tensors) Args: data: any picklable object Returns: list[

3x3 convolution with padding

5x5 convolution with padding

7x7 convolution with padding

Inputs: - input_labels: Variable long (batch, seq_len) Outputs: - output : Varia

evaluate dataset using different methods based on dataset type. Args: dataset: Dataset object predictions(list[BoxList]): each

tensors can be an ImageList, a torch.Tensor or an iterable of Tensors. It can't be a numpy array. When tensors is an iterable of Tenso

Accumulate per image evaluation results and store the result in self.eval.

Performs all_gather operation on the provided tensors. *** Warning ***: torch.distributed.all_gather has no gradient.