Caffe2 - (二十四) Detectron 之 utils 函数(2)

1. env.py


"""Environment helper functions."""from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from __future__ import unicode_literalsimport imp
import os
import sysdef get_runtime_dir():"""寻找运行时的工作路径."""return sys.path[0]def get_py_bin_ext():"""寻找 python 的二进制扩展文件."""return '.py'def set_up_matplotlib():""" matplotlib 设置."""import matplotlib# 采用非交互的后端 non-interactive backendmatplotlib.use('Agg')def exit_on_error():"""出现错误时，退出 detectron tool."""sys.exit(1)def import_nccl_ops():"""导入 NCCL ops.由于 NCCL 依赖已经在 Caffe2 gpu lib 中编译，不需要再加载 NCCL ops."""passdef get_caffe2_dir():"""寻找 Caffe2 所在路径."""_fp, c2_path, _desc = imp.find_module('caffe2')assert os.path.exists(c2_path), \'Caffe2 not found at \'{}\''.format(c2_path)c2_dir = os.path.dirname(os.path.abspath(c2_path))return c2_dirdef get_detectron_ops_lib():"""寻找 Detectron ops library 库路径."""c2_dir = get_caffe2_dir()detectron_ops_lib = os.path.join(c2_dir, 'lib/libcaffe2_detectron_ops_gpu.so')assert os.path.exists(detectron_ops_lib), \('Detectron ops lib not found at \'{}\'; make sure that your Caffe2 ''version includes Detectron module').format(detectron_ops_lib)return detectron_ops_libdef get_custom_ops_lib():"""寻找自定义的 osp library 库路径."""lib_dir, _utils = os.path.split(os.path.dirname(__file__))custom_ops_lib = os.path.join(lib_dir, 'build/libcaffe2_detectron_custom_ops_gpu.so')assert os.path.exists(custom_ops_lib), \'Custom ops lib not found at \'{}\''.format(custom_ops_lib)return custom_ops_lib

2. c2.py

"""Helpful utilities for working with Caffe2."""from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from __future__ import unicode_literalsfrom six import string_types
import contextlibfrom caffe2.proto import caffe2_pb2
from caffe2.python import core
from caffe2.python import dyndep
from caffe2.python import scopeimport utils.env as envudef import_contrib_ops():"""导入 Detectron 所需的 contrib ops."""envu.import_nccl_ops()def import_detectron_ops():"""导入 Detectron ops."""detectron_ops_lib = envu.get_detectron_ops_lib()dyndep.InitOpsLibrary(detectron_ops_lib)def import_custom_ops():"""导入自定义的 ops."""custom_ops_lib = envu.get_custom_ops_lib()dyndep.InitOpsLibrary(custom_ops_lib)def SuffixNet(name, net, prefix_len, outputs):"""从给定的 net 返回新 Net. 新 Net 只包括移除 first `prefix_len` 个 ops 后的 ops.新 Net 是 net 的一个后缀suffix.在 outputs 中的 Blobs 作为 external outpout blobs 被注册."""outputs = BlobReferenceList(outputs)for output in outputs:assert net.BlobIsDefined(output)new_net = net.Clone(name)del new_net.Proto().op[:]del new_net.Proto().external_input[:]del new_net.Proto().external_output[:]# 添加 suffix opsnew_net.Proto().op.extend(net.Proto().op[prefix_len:])# 添加 external input blobs# 将任何未定义的 blobs 作为 external inputsinput_names = [i for op in new_net.Proto().op for i in op.inputif not new_net.BlobIsDefined(i)]new_net.Proto().external_input.extend(input_names)# 添加 external output blobsoutput_names = [str(o) for o in outputs]new_net.Proto().external_output.extend(output_names)return new_net, [new_net.GetBlobRef(o) for o in output_names]def BlobReferenceList(blob_ref_or_list):"""将参数以 BlobReferences 列表的形式返回."""if isinstance(blob_ref_or_list, core.BlobReference):return [blob_ref_or_list]elif type(blob_ref_or_list) in (list, tuple):for b in blob_ref_or_list:assert isinstance(b, core.BlobReference)return blob_ref_or_listelse:raise TypeError('blob_ref_or_list must be a BlobReference or a list/tuple of BlobReferences')def UnscopeName(possibly_scoped_name):"""从一个(可能的)作用域名字中移除任何名字. Remove any name scoping from a (possibly) scoped name如将名字 'gpu_0/foo' 转化为 'foo'."""assert isinstance(possibly_scoped_name, string_types)return possibly_scoped_name[possibly_scoped_name.rfind(scope._NAMESCOPE_SEPARATOR) + 1:]@contextlib.contextmanager
def NamedCudaScope(gpu_id):"""创建 GPU name scope 和 CUDA device scope.用于 reduce `with ...` nesting levels."""with GpuNameScope(gpu_id):with CudaScope(gpu_id):yield@contextlib.contextmanager
def GpuNameScope(gpu_id):"""创建 GPU device `gpu_id` 的名字域 name scope."""with core.NameScope('gpu_{:d}'.format(gpu_id)):yield@contextlib.contextmanager
def CudaScope(gpu_id):"""创建 GPU device `gpu_id` 的 CUDA device scope."""gpu_dev = CudaDevice(gpu_id)with core.DeviceScope(gpu_dev):yield@contextlib.contextmanager
def CpuScope():"""创建 CPU device scope."""cpu_dev = core.DeviceOption(caffe2_pb2.CPU)with core.DeviceScope(cpu_dev):yielddef CudaDevice(gpu_id):"""创建 Cuda device.选择 gpud_id 设备."""return core.DeviceOption(caffe2_pb2.CUDA, gpu_id)def gauss_fill(std):"""减少冗余.Gaussian fill helper"""return ('GaussianFill', {'std': std})def const_fill(value):"""减少冗余.Constant fill helper."""return ('ConstantFill', {'value': value})

3. io.py

"""IO utilities."""from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from __future__ import unicode_literalsimport cPickle as pickle
import hashlib
import logging
import os
import re
import sys
import urllib2logger = logging.getLogger(__name__)# 下载 Detectron 模型的 base url.
_DETECTRON_S3_BASE_URL = 'https://s3-us-west-2.amazonaws.com/detectron'def save_object(obj, file_name):"""序列化 Python 对象object，进行存储."""file_name = os.path.abspath(file_name)with open(file_name, 'wb') as f:pickle.dump(obj, f, pickle.HIGHEST_PROTOCOL)def cache_url(url_or_file, cache_dir):"""根据 URL 下载文件到 cache_dir，并返回下载缓存文件的路径.如果参数不是 URL，则直接返回."""is_url = re.match(r'^(?:http)s?://', url_or_file, re.IGNORECASE) is not Noneif not is_url:return url_or_fileurl = url_or_fileassert url.startswith(_DETECTRON_S3_BASE_URL), \('Detectron only automatically caches URLs in the Detectron S3 ''bucket: {}').format(_DETECTRON_S3_BASE_URL)cache_file_path = url.replace(_DETECTRON_S3_BASE_URL, cache_dir)if os.path.exists(cache_file_path):assert_cache_file_is_ok(url, cache_file_path) # 检验 cache file 的hash 值.return cache_file_pathcache_file_dir = os.path.dirname(cache_file_path)if not os.path.exists(cache_file_dir):os.makedirs(cache_file_dir)logger.info('Downloading remote file {} to {}'.format(url, cache_file_path))download_url(url, cache_file_path)assert_cache_file_is_ok(url, cache_file_path)return cache_file_pathdef assert_cache_file_is_ok(url, file_path):"""检验 cache file 的 hash 值是否正确.文件已经缓存，验证其 md3sum 是否匹配，并返回其 local path."""cache_file_md5sum = _get_file_md5sum(file_path)ref_md5sum = _get_reference_md5sum(url)assert cache_file_md5sum == ref_md5sum, \('Target URL {} appears to be downloaded to the local cache file ''{}, but the md5 hash of the local file does not match the ''reference (actual: {} vs. expected: {}). You may wish to delete ''the cached file and try again to trigger automatic ''download.').format(url, file_path, cache_file_md5sum, ref_md5sum)def _progress_bar(count, total):"""显示下载进度.参考:https://stackoverflow.com/questions/3173320/text-progress-bar-in-the-console/27871113"""bar_len = 60filled_len = int(round(bar_len * count / float(total)))percents = round(100.0 * count / float(total), 1)bar = '=' * filled_len + '-' * (bar_len - filled_len)sys.stdout.write('  [{}] {}% of {:.1f}MB file  \r'.format(bar, percents, total / 1024 / 1024) )sys.stdout.flush()if count >= total:sys.stdout.write('\n')def download_url(url, dst_file_path, chunk_size=8192, progress_hook=_progress_bar):"""下载 URL，并写入 dst_file_path.参考:https://stackoverflow.com/questions/2028517/python-urllib2-progress-hook"""response = urllib2.urlopen(url)total_size = response.info().getheader('Content-Length').strip()total_size = int(total_size)bytes_so_far = 0with open(dst_file_path, 'wb') as f:while 1:chunk = response.read(chunk_size)bytes_so_far += len(chunk)if not chunk:breakif progress_hook:progress_hook(bytes_so_far, total_size)f.write(chunk)return bytes_so_fardef _get_file_md5sum(file_name):"""计算文件的 md5 hash 值."""hash_obj = hashlib.md5()with open(file_name, 'r') as f:hash_obj.update(f.read())return hash_obj.hexdigest()def _get_reference_md5sum(url):"""根据惯例，url 的 md5 hash 值保存在 url + '.md5sum'."""url_md5sum = url + '.md5sum'md5sum = urllib2.urlopen(url_md5sum).read().strip()return md5sum

4. keypoints.py

"""Keypoint utilities (somewhat specific to COCO keypoints)."""from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from __future__ import unicode_literalsimport cv2
import numpy as npfrom core.config import cfg
import utils.blob as blob_utilsdef get_keypoints():"""获取 COCO kyepoints 以及其 left/right 翻转的对应映射.test 中 keypoints 不包括在 COCO json 中，这里进行提供."""keypoints = [ # 18 joints'nose','left_eye','right_eye','left_ear','right_ear','left_shoulder','right_shoulder','left_elbow','right_elbow','left_wrist','right_wrist','left_hip','right_hip','left_knee','right_knee','left_ankle','right_ankle']keypoint_flip_map = {'left_eye': 'right_eye','left_ear': 'right_ear','left_shoulder': 'right_shoulder','left_elbow': 'right_elbow','left_wrist': 'right_wrist','left_hip': 'right_hip','left_knee': 'right_knee','left_ankle': 'right_ankle'}return keypoints, keypoint_flip_mapdef get_person_class_index():"""COCO 中 person class 的索引值 - 1."""return 1def flip_keypoints(keypoints, keypoint_flip_map, keypoint_coords, width):"""left/right 翻转 keypoints 坐标.keypoints 和 keypoints_flip_map 由 get_keypoints() 得到."""flipped_kps = keypoint_coords.copy()for lkp, rkp in keypoint_flip_map.items():lid = keypoints.index(lkp)rid = keypoints.index(rkp)flipped_kps[:, :, lid] = keypoint_coords[:, :, rid]flipped_kps[:, :, rid] = keypoint_coords[:, :, lid]# 翻转 x 坐标flipped_kps[:, 0, :] = width - flipped_kps[:, 0, :] - 1# 保持 COCO 格式，即，if visibility == 0, then x, y = 0inds = np.where(flipped_kps[:, 2, :] == 0)flipped_kps[inds[0], 0, inds[1]] = 0return flipped_kpsdef flip_heatmaps(heatmaps):"""水平翻转 heatmaps."""keypoints, flip_map = get_keypoints()heatmaps_flipped = heatmaps.copy()for lkp, rkp in flip_map.items():lid = keypoints.index(lkp)rid = keypoints.index(rkp)heatmaps_flipped[:, rid, :, :] = heatmaps[:, lid, :, :]heatmaps_flipped[:, lid, :, :] = heatmaps[:, rid, :, :]heatmaps_flipped = heatmaps_flipped[:, :, :, ::-1]return heatmaps_flippeddef heatmaps_to_keypoints(maps, rois):"""从 heatmaps 得到预测的 keypoints 位置.输出格式为：(#rois, 4, #keypoints) - 4 rows 对应于每个 keypoints 的 (x, y, logit, prob).该函数将 HEATMAP_SIZE x HEATMAP_SIZE image 中的离散坐标转换为连续的 keypoints 坐标.采用 Heckbert 1990: c = d + 0.5(其中，d 是离散坐标，c 是连续坐标.) 的变换，来保持 keypoints_to_heatmap_labels 的一致性."""offset_x = rois[:, 0]offset_y = rois[:, 1]widths = rois[:, 2] - rois[:, 0]heights = rois[:, 3] - rois[:, 1]widths = np.maximum(widths, 1)heights = np.maximum(heights, 1)widths_ceil = np.ceil(widths)heights_ceil = np.ceil(heights)# NCHW to NHWC for use with OpenCVmaps = np.transpose(maps, [0, 2, 3, 1])min_size = cfg.KRCNN.INFERENCE_MIN_SIZExy_preds = np.zeros((len(rois), 4, cfg.KRCNN.NUM_KEYPOINTS), dtype=np.float32)for i in range(len(rois)):if min_size > 0:roi_map_width = int(np.maximum(widths_ceil[i], min_size))roi_map_height = int(np.maximum(heights_ceil[i], min_size))else:roi_map_width = widths_ceil[i]roi_map_height = heights_ceil[i]width_correction = widths[i] / roi_map_widthheight_correction = heights[i] / roi_map_heightroi_map = cv2.resize(maps[i], (roi_map_width, roi_map_height),interpolation=cv2.INTER_CUBIC)# Bring back to CHWroi_map = np.transpose(roi_map, [2, 0, 1])roi_map_probs = scores_to_probs(roi_map.copy())w = roi_map.shape[2]for k in range(cfg.KRCNN.NUM_KEYPOINTS):pos = roi_map[k, :, :].argmax()x_int = pos % wy_int = (pos - x_int) // wassert (roi_map_probs[k, y_int, x_int] == roi_map_probs[k, :, :].max())x = (x_int + 0.5) * width_correctiony = (y_int + 0.5) * height_correctionxy_preds[i, 0, k] = x + offset_x[i]xy_preds[i, 1, k] = y + offset_y[i]xy_preds[i, 2, k] = roi_map[k, y_int, x_int]xy_preds[i, 3, k] = roi_map_probs[k, y_int, x_int]return xy_predsdef keypoints_to_heatmap_labels(keypoints, rois):"""对 target heatmap 中的 keypoints 位置进行编码，以用于 SoftmaxWithLoss.将 keypoints 从连续图片坐标的半开区间 [x1, x2)，映射到离散图片坐标的闭区间 [0, HEATMAP_SIZE - 1].采用  Heckbert 1990 ("What is the coordinate of a pixel?") 的变换方案: d = floor(c) 和 c = d + 0.5(其中，d 是离散坐标，c 是连续坐标.)"""assert keypoints.shape[2] == cfg.KRCNN.NUM_KEYPOINTSshape = (len(rois), cfg.KRCNN.NUM_KEYPOINTS)heatmaps = blob_utils.zeros(shape)weights = blob_utils.zeros(shape)offset_x = rois[:, 0]offset_y = rois[:, 1]scale_x = cfg.KRCNN.HEATMAP_SIZE / (rois[:, 2] - rois[:, 0])scale_y = cfg.KRCNN.HEATMAP_SIZE / (rois[:, 3] - rois[:, 1])for kp in range(keypoints.shape[2]):vis = keypoints[:, 2, kp] > 0x = keypoints[:, 0, kp].astype(np.float32)y = keypoints[:, 1, kp].astype(np.float32)# 由于使用了 floor 处理，如果 keypoints 正好位于 roi 的right 或 bottom 边界上，则将对其平移 eps，以保证其位于 groundtruth hetmap 上.x_boundary_inds = np.where(x == rois[:, 2])[0]y_boundary_inds = np.where(y == rois[:, 3])[0]x = (x - offset_x) * scale_xx = np.floor(x)if len(x_boundary_inds) > 0:x[x_boundary_inds] = cfg.KRCNN.HEATMAP_SIZE - 1y = (y - offset_y) * scale_yy = np.floor(y)if len(y_boundary_inds) > 0:y[y_boundary_inds] = cfg.KRCNN.HEATMAP_SIZE - 1valid_loc = np.logical_and(np.logical_and(x >= 0, y >= 0),np.logical_and(x < cfg.KRCNN.HEATMAP_SIZE, y < cfg.KRCNN.HEATMAP_SIZE))valid = np.logical_and(valid_loc, vis)valid = valid.astype(np.int32)lin_ind = y * cfg.KRCNN.HEATMAP_SIZE + xheatmaps[:, kp] = lin_ind * validweights[:, kp] = validreturn heatmaps, weightsdef scores_to_probs(scores):"""将 CxHxW 的 scores 转换为空间概率."""channels = scores.shape[0]for c in range(channels):temp = scores[c, :, :]max_score = temp.max()temp = np.exp(temp - max_score) / np.sum(np.exp(temp - max_score))scores[c, :, :] = tempreturn scoresdef nms_oks(kp_predictions, rois, thresh):"""基于 kp predictions 进行 NMS."""scores = np.mean(kp_predictions[:, 2, :], axis=1)order = scores.argsort()[::-1]keep = []while order.size > 0:i = order[0]keep.append(i)ovr = compute_oks(kp_predictions[i], rois[i], kp_predictions[order[1:]], rois[order[1:]])inds = np.where(ovr <= thresh)[0]order = order[inds + 1]return keepdef compute_oks(src_keypoints, src_roi, dst_keypoints, dst_roi):"""计算预测的 keypoints 关于 gt_keypoints 的 OKS.src_keypoints: 4xKsrc_roi: 4x1dst_keypoints: Nx4xKdst_roi: Nx4"""sigmas = np.array([.26, .25, .25, .35, .35, .79, .79, .72, .72, .62, .62, 1.07, 1.07, .87, .87, .89, .89]) / 10.0vars = (sigmas * 2)**2# 面积areasrc_area = (src_roi[2] - src_roi[0] + 1) * (src_roi[3] - src_roi[1] + 1)# 如果 keypoints visible, 计算 per-keypoints 间的距离.dx = dst_keypoints[:, 0, :] - src_keypoints[0, :]dy = dst_keypoints[:, 1, :] - src_keypoints[1, :]e = (dx**2 + dy**2) / vars / (src_area + np.spacing(1)) / 2e = np.sum(np.exp(-e), axis=1) / e.shape[1]return e

5. segm.py

"""
处理 COCO 格式的 segmentation masks 的函数.
所使用到的项有:- mask: 2D numpy array 格式的二值 mask. a binary mask encoded as a 2D numpy array- segm: segmentation mask 格式，(COCO 有两种 segmentation mask 格式：polygon or RLE)- polygon: COCO 的多边形格式(polygon format)- RLE: COCO's run length encoding format
"""from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from __future__ import unicode_literalsimport numpy as npimport pycocotools.mask as mask_utildef flip_segms(segms, height, width):"""对 masks 列表中的各 mask 进行 left/right 翻转."""def _flip_poly(poly, width):flipped_poly = np.array(poly)flipped_poly[0::2] = width - np.array(poly[0::2]) - 1return flipped_poly.tolist()def _flip_rle(rle, height, width):if 'counts' in rle and type(rle['counts']) == list:# Magic RLE 格式，利用 COCO API 的 showAnns 函数来处理.rle = mask_util.frPyObjects([rle], height, width)mask = mask_util.decode(rle)mask = mask[:, ::-1, :]rle = mask_util.encode(np.array(mask, order='F', dtype=np.uint8))return rleflipped_segms = []for segm in segms:if type(segm) == list:# 多边形格式 Polygon formatflipped_segms.append([_flip_poly(poly, width) for poly in segm])else:# RLE formatassert type(segm) == dictflipped_segms.append(_flip_rle(segm, height, width))return flipped_segmsdef polys_to_mask(polygons, height, width):"""将 COCO 的多边形分割(polygon segmentation) 格式转换为数据类型为 np.float32 的 2D numpy array 的二值 mask.多边形分割(polygon segmentation) 被理解为在 height x width 图片中的封闭区域.得到的 mask shape 是 (height, width)."""rle = mask_util.frPyObjects(polygons, height, width)mask = np.array(mask_util.decode(rle), dtype=np.float32)# Flatten in case polygons was a listmask = np.sum(mask, axis=2)mask = np.array(mask > 0, dtype=np.float32)return maskdef mask_to_bbox(mask):"""计算二值 mask 的边界框 bounding box."""xs = np.where(np.sum(mask, axis=0) > 0)[0]ys = np.where(np.sum(mask, axis=1) > 0)[0]if len(xs) == 0 or len(ys) == 0:return Nonex0 = xs[0]x1 = xs[-1]y0 = ys[0]y1 = ys[-1]return np.array((x0, y0, x1, y1), dtype=np.float32)def polys_to_mask_wrt_box(polygons, box, M):"""将 COCO 多边形分割(polygon segmentation)格式转换为数据类型为 np.float32 的 2D numpy array 的二值 mask.多边形分割(polygon segmentation) 被理解为在给定 box 的封闭区域，大小为 M x M 的 mask.得到的 mask shape 是 (M, M)."""w = box[2] - box[0]h = box[3] - box[1]w = np.maximum(w, 1)h = np.maximum(h, 1)polygons_norm = []for poly in polygons:p = np.array(poly, dtype=np.float32)p[0::2] = (p[0::2] - box[0]) * M / wp[1::2] = (p[1::2] - box[1]) * M / hpolygons_norm.append(p)rle = mask_util.frPyObjects(polygons_norm, M, M)mask = np.array(mask_util.decode(rle), dtype=np.float32)# Flatten in case polygons was a listmask = np.sum(mask, axis=2)mask = np.array(mask > 0, dtype=np.float32)return maskdef polys_to_boxes(polys):"""将多边形列表(polygons list) 转换为边界框 bounding boxes array."""boxes_from_polys = np.zeros((len(polys), 4), dtype=np.float32)for i in range(len(polys)):poly = polys[i]x0 = min(min(p[::2]) for p in poly)x1 = max(max(p[::2]) for p in poly)y0 = min(min(p[1::2]) for p in poly)y1 = max(max(p[1::2]) for p in poly)boxes_from_polys[i, :] = [x0, y0, x1, y1]return boxes_from_polysdef rle_mask_voting(top_masks, all_masks, all_dets, iou_thresh, binarize_thresh, method='AVG'):"""组合 all_masks 中多个重叠 masks 来返回新的 mask(对应于 top_masks).支持两种 masks 组合方法：- AVG - 使用重叠 mask 像素的加权平均值(weighted average of overlapping mask pixels)- UNION - 所有 mask 像素的并集(union of all mask pixels)s."""if len(top_masks) == 0:returnall_not_crowd = [False] * len(all_masks)top_to_all_overlaps = mask_util.iou(top_masks, all_masks, all_not_crowd)decoded_all_masks = [np.array(mask_util.decode(rle), dtype=np.float32) for rle in all_masks]decoded_top_masks = [np.array(mask_util.decode(rle), dtype=np.float32) for rle in top_masks]all_boxes = all_dets[:, :4].astype(np.int32)all_scores = all_dets[:, 4]# Fill box support with weightsmask_shape = decoded_all_masks[0].shapemask_weights = np.zeros((len(all_masks), mask_shape[0], mask_shape[1]))for k in range(len(all_masks)):ref_box = all_boxes[k]x_0 = max(ref_box[0], 0)x_1 = min(ref_box[2] + 1, mask_shape[1])y_0 = max(ref_box[1], 0)y_1 = min(ref_box[3] + 1, mask_shape[0])mask_weights[k, y_0:y_1, x_0:x_1] = all_scores[k]mask_weights = np.maximum(mask_weights, 1e-5)top_segms_out = []for k in range(len(top_masks)):# 空 mask 的极端情况 Corner case of empty maskif decoded_top_masks[k].sum() == 0:top_segms_out.append(top_masks[k])continueinds_to_vote = np.where(top_to_all_overlaps[k] >= iou_thresh)[0]# Only matches itselfif len(inds_to_vote) == 1:top_segms_out.append(top_masks[k])continuemasks_to_vote = [decoded_all_masks[i] for i in inds_to_vote]if method == 'AVG':ws = mask_weights[inds_to_vote]soft_mask = np.average(masks_to_vote, axis=0, weights=ws)mask = np.array(soft_mask > binarize_thresh, dtype=np.uint8)elif method == 'UNION':# Any pixel that's on joins the masksoft_mask = np.sum(masks_to_vote, axis=0)mask = np.array(soft_mask > 1e-5, dtype=np.uint8)else:raise NotImplementedError('Method {} is unknown'.format(method))rle = mask_util.encode(np.array(mask[:, :, np.newaxis], order='F'))[0]top_segms_out.append(rle)return top_segms_outdef rle_mask_nms(masks, dets, thresh, mode='IOU'):"""基于 masks 间的重叠度量(overlap measurement) 进行贪婪 NMS 处理.度量类型有 mode 来定义，有：- 标准 IoU(standard intersection over union) - IOMA (intersection over mininum area)"""if len(masks) == 0:return []if len(masks) == 1:return [0]if mode == 'IOU':# 计算 ious[m1, m2] = area(intersect(m1, m2)) / area(union(m1, m2))all_not_crowds = [False] * len(masks)ious = mask_util.iou(masks, masks, all_not_crowds)elif mode == 'IOMA':# 计算 ious[m1, m2] = area(intersect(m1, m2)) / min(area(m1), area(m2))all_crowds = [True] * len(masks)# ious[m1, m2] = area(intersect(m1, m2)) / area(m2)ious = mask_util.iou(masks, masks, all_crowds)# ... = max(area(intersect(m1, m2)) / area(m2),#           area(intersect(m2, m1)) / area(m1))ious = np.maximum(ious, ious.transpose())elif mode == 'CONTAINMENT':# 计算 ious[m1, m2] = area(intersect(m1, m2)) / area(m2)# 度量了 m2 在 m1 中的部分(Which measures how much m2 is contained inside m1)all_crowds = [True] * len(masks)ious = mask_util.iou(masks, masks, all_crowds)else:raise NotImplementedError('Mode {} is unknown'.format(mode))scores = dets[:, 4]order = np.argsort(-scores)keep = []while order.size > 0:i = order[0]keep.append(i)ovr = ious[i, order[1:]]inds_to_keep = np.where(ovr <= thresh)[0]order = order[inds_to_keep + 1]return keepdef rle_masks_to_boxes(masks):"""计算在 RLE 编码的 masks 列表中各 mask 的边界框bounding box."""if len(masks) == 0:return []decoded_masks = [np.array(mask_util.decode(rle), dtype=np.float32) for rle in masks]def get_bounds(flat_mask):inds = np.where(flat_mask > 0)[0]return inds.min(), inds.max()boxes = np.zeros((len(decoded_masks), 4))keep = [True] * len(decoded_masks)for i, mask in enumerate(decoded_masks):if mask.sum() == 0:keep[i] = Falsecontinueflat_mask = mask.sum(axis=0)x0, x1 = get_bounds(flat_mask)flat_mask = mask.sum(axis=1)y0, y1 = get_bounds(flat_mask)boxes[i, :] = (x0, y0, x1, y1)return boxes, np.where(keep)[0]

Caffe2 - (二十四) Detectron 之 utils 函数(2)相关推荐

C语言试题二十四之编写一个函数unsigned function(unsigned w),w使一个大于10的无符号整数，若w是n(n≥2)位的整数，则函数求出w后n－1位的数作为函数值返回。
1. 题目请编写一个函数unsigned function(unsigned w),w使一个大于10的无符号整数,若w是n(n≥2)位的整数,则函数求出w后n-1位的数作为函数值返回. 比如:w是1 ...
【Excel2019(二十四)：宏表函数】【利用宏表函数获取信息+宏表函数常见应用】
上一篇:[Excel2019(二十三):饼图美化与PPT图表][双坐标柱形图的补充知识+饼图美化+PPT中的图表] 文章目录利用宏表函数获取信息 get.cell函数计算颜色提取公式常用的Ty ...
异常处理程序和软件异常——Windows核心编程学习手札之二十四
异常处理程序和软件异常 --Windows核心编程学习手札之二十四 CPU负责捕捉无效内存访问和用0除一个数值这种错误,并相应引发一个异常作为对错误的反应,CPU引发的异常称为硬件异常(hardwar ...
数字图像处理领域的二十四个典型算法及vc实现、第一章
数字图像处理领域的二十四个典型算法及vc实现.第一章作者:July 二零一一年二月二十六日. 参考:百度百科.维基百科.vc数字图像处理. --------------------------- ...
[系统安全] 二十四.逆向分析之OllyDbg调试INT3断点、反调试、硬件断点与内存断点
您可能之前看到过我写的类似文章,为什么还要重复撰写呢?只是想更好地帮助初学者了解病毒逆向分析和系统安全,更加成体系且不破坏之前的系列.因此,我重新开设了这个专栏,准备系统整理和深入学习系统安全.逆向分 ...
OpenCV学习(二十四）：角点检测(Corner Detection):cornerHarris(),goodFeatureToTrack()
OpenCV学习(二十四 ):角点检测(Corner Detection):cornerHarris(),goodFeatureToTrack() 参考博客: Harris角点检测原理详解 Harri ...
鸡啄米之VS2010/MFC编程入门之二十四（常用控件：列表框控件ListBox）
目录一.目的: 1.点击列表框某个变量后,编辑框就显示出来这个变量名字一.参考: 1.VS2010/MFC编程入门之二十四(常用控件:列表框控件ListBox) ①总结:good:亲测有效,适合多 ...
数字图像处理领域的二十四个典型算法
数字图像处理领域的二十四个典型算法及vc实现.第一章一.256色转灰度图二.Walsh变换三.二值化变换四.阈值变换五.傅立叶变换六.离散余弦变换数字图像处理领域的二十四个典型算法及vc ...
matlab火星漫游车转向控制,OSG开发笔记（二十四）：OSG漫游之平移与转向
若该文为原创文章,未经允许不得转载原博主博客地址:https://blog.csdn.net/qq21497936 本文章博客地址:https://blog.csdn.net/qq21497936/ ...
【Visual C++】游戏开发五十七浅墨DirectX教程二十四打造游戏GUI界面（二）
本系列文章由zhmxy555(毛星云)编写,转载请注明出处. 文章链接: http://blog.csdn.net/poem_qianmo/article/details/16922703 作者:毛星 ...

Caffe2 - (二十四) Detectron 之 utils 函数(2)

Caffe2 - (二十四) Detectron 之 utils 函数(2)

1. env.py

2. c2.py

3. io.py

4. keypoints.py

5. segm.py

Caffe2 - (二十四) Detectron 之 utils 函数(2)相关推荐

最新文章

热门文章