Add a downsample layer to the backbone as per what SSD does.

Add a downsample layer to the backbone as per what SSD does.

TODO: Need to make sure that this works as intended.

Custom collate fn for dealing with batches of images that have a different number of associated object annotations (bounding boxes). Argument

Disables the given function name fom being considered for the average or outputted in print_stats.

Enables function names disabled by disable.

Args: - x: The convOut from a layer in the backbone network Size: [batch_size, in_channels, conv_h, conv_w])

Args: - x: The convOut from a layer in the backbone network Size: [batch_size, in_channels, conv_h, conv_w])

Args: - convouts (list): A list of convouts for the corresponding layers in in_channels. Returns: - A list of

Args: - convouts (list): A list of convouts for the corresponding layers in in_channels. Returns: - A list of

Args: - convouts (list): A list of convouts for the corresponding layers in in_channels. Returns: - A list of

The input should be of size [batch_size, 3, img_h, img_w]

Returns a list of convouts for each layer.

Returns a list of convouts for each layer.

Returns a list of convouts for each layer.

Returns a list of convouts for each layer.

Multibox Loss Args: predictions (tuple): A tuple containing loc preds, conf preds, mask preds, and prior boxes from SS

Indexes a tensor by a 2d index. In effect, this does out[i, j] = src[i, idx[i, j]] Both src and idx should have the same si

Initializes the backbone weights for training.

The path here comes from detectron. So we load it differently.

Initializes the backbone weights for training.

Initializes the backbone weights for training.

Prints the current timing information into a table.

Returns the original annotation of image at index Note: not using self.__getitem__(), as any transformations passed in could mess up

Returns the original annotation of image at index Note: not using self.__getitem__(), as any transformations passed in could mess up

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

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

Resets the current timer. Call this at the start of an iteration.