CIntToPy */

BufferGetAndValidate */

CIntToPy */

CIntToPy */

ExtTypeTest */

Return an roidb corresponding to the json dataset. Optionally: - include ground truth boxes in the roidb - add proposals specifi

Save a Python object by pickling it.

GetBuiltinName */

GetBuiltinName */

CIntToPy */

Take the mean and reset list empty

Make a stage consist of `nblocks` residual blocks. Returns: - stage module: an nn.Sequentail module of residual blocks - final out

Prepare the bbox for testing

Infer instance keypoint poses. This function must be called after im_detect_bbox as it assumes that the Caffe2 workspace is already populated

Infer instance segmentation masks. This function must be called after im_detect_bbox as it assumes that the Caffe2 workspace is already populated

CIntToPy */

Call this function in your script after you have finished setting all cfg values that are necessary (e.g., merging a config from a file, merging

Helper to return a function object by name. func_name must identify a function in this module or the path to a function relative to the base '

GetItemInt */

RaiseArgTupleInvalid */

Distributes a set of RoIs across FPN pyramid levels by creating new level specific RoI blobs. Arguments: blobs (dict): dictionary of

Distribute rois over the different FPN levels.

Converts RoIs into network inputs. Arguments: im_rois (ndarray): R x 4 matrix of RoIs in original image coordinates im_scale_fact

Add results for an image to the set of all results at the specified index.

Freeze all the weights by setting requires_grad to False

Generates a matrix of anchor boxes in (x1, y1, x2, y2) format. Anchors are centered on stride / 2, have (approximate) sqrt areas of the specified

Performs bbox detection on the horizontally flipped image. Function signature is the same as for im_detect_bbox.

Computes keypoint predictions on the horizontally flipped image. Function signature is the same as for im_detect_keypoints_aug.

Performs mask detection on the horizontally flipped image. Function signature is the same as for im_detect_mask_aug.

Save checkpoint

Update tracked iteration statistics.

The MomentumSGDUpdate op implements the update V as V := mu * V + lr * grad, where mu is the momentum factor, lr is the learning rate, a

IsLittleEndian */

IsLittleEndian */

ParseKeywords */