生成高斯热力图(craft中有使用)+2d heatmap+3d heatmap

一.生成高斯热力图

from math import exp
import numpy as np
import cv2
import osclass GaussianTransformer(object):def __init__(self, imgSize=512, region_threshold=0.4,affinity_threshold=0.2):distanceRatio = 3.34scaledGaussian = lambda x: exp(-(1 / 2) * (x ** 2))self.region_threshold = region_thresholdself.imgSize = imgSizeself.standardGaussianHeat = self._gen_gaussian_heatmap(imgSize, distanceRatio)_, binary = cv2.threshold(self.standardGaussianHeat, region_threshold * 255, 255, 0)np_contours = np.roll(np.array(np.where(binary != 0)), 1, axis=0).transpose().reshape(-1, 2)x, y, w, h = cv2.boundingRect(np_contours)self.regionbox = np.array([[x, y], [x + w, y], [x + w, y + h], [x, y + h]], dtype=np.int32)# print("regionbox", self.regionbox)_, binary = cv2.threshold(self.standardGaussianHeat, affinity_threshold * 255, 255, 0)np_contours = np.roll(np.array(np.where(binary != 0)), 1, axis=0).transpose().reshape(-1, 2)x, y, w, h = cv2.boundingRect(np_contours)self.affinitybox = np.array([[x, y], [x + w, y], [x + w, y + h], [x, y + h]], dtype=np.int32)# print("affinitybox", self.affinitybox)self.oribox = np.array([[0, 0, 1], [imgSize - 1, 0, 1], [imgSize - 1, imgSize - 1, 1], [0, imgSize - 1, 1]],dtype=np.int32)def _gen_gaussian_heatmap(self, imgSize, distanceRatio):scaledGaussian = lambda x: exp(-(1 / 2) * (x ** 2))heat = np.zeros((imgSize, imgSize), np.uint8)for i in range(imgSize):for j in range(imgSize):distanceFromCenter = np.linalg.norm(np.array([i - imgSize / 2, j - imgSize / 2]))distanceFromCenter = distanceRatio * distanceFromCenter / (imgSize / 2)scaledGaussianProb = scaledGaussian(distanceFromCenter)heat[i, j] = np.clip(scaledGaussianProb * 255, 0, 255)return heatdef _test(self):sigma = 10spread = 3extent = int(spread * sigma)center = spread * sigma / 2gaussian_heatmap = np.zeros([extent, extent], dtype=np.float32)for i_ in range(extent):for j_ in range(extent):gaussian_heatmap[i_, j_] = 1 / 2 / np.pi / (sigma ** 2) * np.exp(-1 / 2 * ((i_ - center - 0.5) ** 2 + (j_ - center - 0.5) ** 2) / (sigma ** 2))gaussian_heatmap = (gaussian_heatmap / np.max(gaussian_heatmap) * 255).astype(np.uint8)images_folder = os.path.abspath(os.path.dirname(__file__)) + '/images'threshhold_guassian = cv2.applyColorMap(gaussian_heatmap, cv2.COLORMAP_JET)cv2.imwrite(os.path.join(images_folder, 'test_guassian.jpg'), threshhold_guassian)def add_region_character(self, image, target_bbox, regionbox=None):if np.any(target_bbox < 0) or np.any(target_bbox[:, 0] > image.shape[1]) or np.any(target_bbox[:, 1] > image.shape[0]):return imageaffi = Falseif regionbox is None:regionbox = self.regionbox.copy()else:affi = TrueM = cv2.getPerspectiveTransform(np.float32(regionbox), np.float32(target_bbox))oribox = np.array([[[0, 0], [self.imgSize - 1, 0], [self.imgSize - 1, self.imgSize - 1], [0, self.imgSize - 1]]],dtype=np.float32)test1 = cv2.perspectiveTransform(np.array([regionbox], np.float32), M)[0]real_target_box = cv2.perspectiveTransform(oribox, M)[0]# print("test\ntarget_bbox", target_bbox, "\ntest1", test1, "\nreal_target_box", real_target_box)real_target_box = np.int32(real_target_box)real_target_box[:, 0] = np.clip(real_target_box[:, 0], 0, image.shape[1])real_target_box[:, 1] = np.clip(real_target_box[:, 1], 0, image.shape[0])# warped = cv2.warpPerspective(self.standardGaussianHeat.copy(), M, (image.shape[1], image.shape[0]))# warped = np.array(warped, np.uint8)# image = np.where(warped > image, warped, image)if np.any(target_bbox[0] < real_target_box[0]) or (target_bbox[3, 0] < real_target_box[3, 0] or target_bbox[3, 1] > real_target_box[3, 1]) or (target_bbox[1, 0] > real_target_box[1, 0] or target_bbox[1, 1] < real_target_box[1, 1]) or (target_bbox[2, 0] > real_target_box[2, 0] or target_bbox[2, 1] > real_target_box[2, 1]):# if False:warped = cv2.warpPerspective(self.standardGaussianHeat.copy(), M, (image.shape[1], image.shape[0]))warped = np.array(warped, np.uint8)image = np.where(warped > image, warped, image)# _M = cv2.getPerspectiveTransform(np.float32(regionbox), np.float32(_target_box))# warped = cv2.warpPerspective(self.standardGaussianHeat.copy(), _M, (width, height))# warped = np.array(warped, np.uint8)## # if affi:# # print("warped", warped.shape, real_target_box, target_bbox, _target_box)# # cv2.imshow("1123", warped)# # cv2.waitKey()# image[ymin:ymax, xmin:xmax] = np.where(warped > image[ymin:ymax, xmin:xmax], warped,#                                        image[ymin:ymax, xmin:xmax])else:xmin = real_target_box[:, 0].min()xmax = real_target_box[:, 0].max()ymin = real_target_box[:, 1].min()ymax = real_target_box[:, 1].max()width = xmax - xminheight = ymax - ymin_target_box = target_bbox.copy()_target_box[:, 0] -= xmin_target_box[:, 1] -= ymin_M = cv2.getPerspectiveTransform(np.float32(regionbox), np.float32(_target_box))warped = cv2.warpPerspective(self.standardGaussianHeat.copy(), _M, (width, height))warped = np.array(warped, np.uint8)if warped.shape[0] != (ymax - ymin) or warped.shape[1] != (xmax - xmin):print("region (%d:%d,%d:%d) warped shape (%d,%d)" % (ymin, ymax, xmin, xmax, warped.shape[1], warped.shape[0]))return image# if affi:# print("warped", warped.shape, real_target_box, target_bbox, _target_box)# cv2.imshow("1123", warped)# cv2.waitKey()image[ymin:ymax, xmin:xmax] = np.where(warped > image[ymin:ymax, xmin:xmax], warped,image[ymin:ymax, xmin:xmax])return imagedef add_affinity_character(self, image, target_bbox):return self.add_region_character(image, target_bbox, self.affinitybox)def add_affinity(self, image, bbox_1, bbox_2):center_1, center_2 = np.mean(bbox_1, axis=0), np.mean(bbox_2, axis=0)tl = np.mean([bbox_1[0], bbox_1[1], center_1], axis=0)bl = np.mean([bbox_1[2], bbox_1[3], center_1], axis=0)tr = np.mean([bbox_2[0], bbox_2[1], center_2], axis=0)br = np.mean([bbox_2[2], bbox_2[3], center_2], axis=0)affinity = np.array([tl, tr, br, bl])return self.add_affinity_character(image, affinity.copy()), np.expand_dims(affinity, axis=0)def generate_region(self, image_size, bboxes):height, width = image_size[0], image_size[1]target = np.zeros([height, width], dtype=np.uint8)for i in range(len(bboxes)):character_bbox = np.array(bboxes[i].copy())for j in range(bboxes[i].shape[0]):target = self.add_region_character(target, character_bbox[j])return targetdef generate_affinity(self, image_size, bboxes, words):height, width = image_size[0], image_size[1]target = np.zeros([height, width], dtype=np.uint8)affinities = []for i in range(len(words)):character_bbox = np.array(bboxes[i])total_letters = 0for char_num in range(character_bbox.shape[0] - 1):target, affinity = self.add_affinity(target, character_bbox[total_letters],character_bbox[total_letters + 1])affinities.append(affinity)total_letters += 1if len(affinities) > 0:affinities = np.concatenate(affinities, axis=0)return target, affinitiesdef saveGaussianHeat(self):images_folder = os.path.abspath(os.path.dirname(__file__)) + '/images'print('==images_folder:', images_folder)if not os.path.exists(images_folder):os.mkdir(images_folder)cv2.imwrite(os.path.join(images_folder, 'standard.jpg'), self.standardGaussianHeat)warped_color = cv2.applyColorMap(self.standardGaussianHeat, cv2.COLORMAP_JET)cv2.polylines(warped_color, [np.reshape(self.regionbox, (-1, 1, 2))], True, (255, 255, 255), thickness=1)cv2.imwrite(os.path.join(images_folder, 'standard_color.jpg'), warped_color)standardGaussianHeat1 = self.standardGaussianHeat.copy()threshhold = self.region_threshold * 255standardGaussianHeat1[standardGaussianHeat1 > 0] = 255threshhold_guassian = cv2.applyColorMap(standardGaussianHeat1, cv2.COLORMAP_JET)cv2.polylines(threshhold_guassian, [np.reshape(self.regionbox, (-1, 1, 2))], True, (255, 255, 255), thickness=1)cv2.imwrite(os.path.join(images_folder, 'threshhold_guassian.jpg'), threshhold_guassian)if __name__ == '__main__':gaussian = GaussianTransformer(512, 0.4, 0.2)gaussian.saveGaussianHeat()gaussian._test()bbox0 = np.array([[[0, 0], [100, 0], [100, 100], [0, 100]]])image = np.zeros((500, 500), np.uint8)# image = gaussian.add_region_character(image, bbox)bbox1 = np.array([[[100, 0], [200, 0], [200, 100], [100, 100]]])bbox2 = np.array([[[100, 100], [200, 100], [200, 200], [100, 200]]])bbox3 = np.array([[[0, 100], [100, 100], [100, 200], [0, 200]]])bbox4 = np.array([[[96, 0], [151, 9], [139, 64], [83, 58]]])# image = gaussian.add_region_character(image, bbox)# print(image.max())image = gaussian.generate_region((500, 500, 1), [bbox3])# target_gaussian_heatmap_color = imgproc.cvt2HeatmapImg(image.copy() / 255)# cv2.imshow("test", target_gaussian_heatmap_color)# cv2.imwrite("test.jpg", target_gaussian_heatmap_color)# cv2.waitKey()

          

  1.标准高斯分布                                             2.伪彩色

二.3d点　生成3d heatmap

注意的是此时3d点是手腕坐标系，取的400是可以正负活动，x,y,z范围是[-200, 200],所以除以400，在加以0.5归一化至[0, 1]


import numpy as np
joints_3d = np.array([[-24.25473, -14.594984, -123.86395],[-21.384483, -2.5870495, -102.83917],[-2.1389189, 0.4295807, -77.805786],[0.4713831, -4.49901, -45.992554],[-24.65406, -7.517185, -131.60638],[-20.059254, 10.334126, -121.49127],[-14.004571, 31.53947, -106.92682],[0.97307205, 54.702316, -72.0885],[-34.38083, -5.5681667, -132.75537],[-36.56296, 15.5307255, -122.979614],[-34.097603, 38.7413, -104.22839],[-23.116486, 59.41091, -62.15027],[-40.734467, -13.705656, -126.29144],[-48.140816, 5.673216, -115.56366],[-52.453285, 28.091465, -97.55463],[-41.134747, 46.38981, -56.097656],[-38.43096, -12.890821, -117.34686],[-44.426872, -1.405302, -101.77527],[-50.584797, 10.186543, -84.22754],[-53.451706, 24.639828, -51.59436],[0., 0., 0.]], dtype=np.float32)
joints_3d_visible = np.array([[1., 1., 1.],[1., 1., 1.],[1., 1., 1.],[1., 1., 1.],[1., 1., 1.],[1., 1., 1.],[1., 1., 1.],[1., 1., 1.],[1., 1., 1.],[1., 1., 1.],[1., 1., 1.],[1., 1., 1.],[1., 1., 1.],[1., 1., 1.],[1., 1., 1.],[1., 1., 1.],[1., 1., 1.],[1., 1., 1.],[1., 1., 1.],[1., 1., 1.],[1., 1., 1.]], dtype=np.float32)
heatmap3d_depth_bound = 400
W, H, D = 64, 64, 64
num_joints = 21
mu_x = (joints_3d[:, 0] / heatmap3d_depth_bound + 0.5) * W
mu_y = (joints_3d[:, 1] / heatmap3d_depth_bound + 0.5) * H
mu_z = (joints_3d[:, 2] / heatmap3d_depth_bound + 0.5) * D
print('==mu_x:', mu_x)
print('==mu_y:', mu_y)
print('==mu_z:', mu_z)
target = np.zeros([num_joints, D, H, W], dtype=np.float32)target_weight = joints_3d_visible[:, 0].astype(np.float32)
# print('==target_weight:', target_weight)
target_weight = target_weight * (mu_z >= 0) * (mu_z < D) * (mu_x >= 0) * (mu_x < W) * (mu_y >= 0) * (mu_y < H)
# print('==target_weight:', target_weight)
# if use_different_joint_weights:
#     target_weight = target_weight * joint_weights
target_weight = target_weight[:, None]sigma = 2.5
# only compute the voxel value near the joints location
tmp_size = 3 * sigma# get neighboring voxels coordinates
x = y = z = np.arange(2 * tmp_size + 1, dtype=np.float32) - tmp_size
# print('==x,y,z:', x, y, z)
# print('==len(x):', len(x))
zz, yy, xx = np.meshgrid(z, y, x)
# print('==xx.shape:', xx.shape)
# print(xx[0])
xx = xx[None, ...].astype(np.float32)  # (1, 2 * tmp_size + 1, 2 * tmp_size + 1,2 * tmp_size + 1, 2 * tmp_size + 1)
yy = yy[None, ...].astype(np.float32)
zz = zz[None, ...].astype(np.float32)
mu_x = mu_x[..., None, None, None]  # (42, 1, 1, 1)
mu_y = mu_y[..., None, None, None]
mu_z = mu_z[..., None, None, None]
xx, yy, zz = xx + mu_x, yy + mu_y, zz + mu_z  # (42, 2 * tmp_size + 1, 2 * tmp_size + 1, 2 * tmp_size + 1)
# print('==np.min(xx):', np.min(xx))
# print('==np.max(xx):', np.max(xx))
# print('==np.min(yy):', np.min(yy))
# print('==np.max(yy):', np.max(yy))
# print('==np.min(zz):', np.min(zz))
# print('==np.max(zz):', np.max(zz))
# round the coordinates
xx = xx.round().clip(0, W - 1)
yy = yy.round().clip(0, H - 1)
zz = zz.round().clip(0, D - 1)# compute the target value near joints
# (42, 2 * tmp_size + 1, 2 * tmp_size + 1, 2 * tmp_size + 1)
local_target = \np.exp(-((xx - mu_x) ** 2 + (yy - mu_y) ** 2 + (zz - mu_z) ** 2) /(2 * sigma ** 2))
# print('==local_target.shape:', local_target.shape)
# import pdb;pdb.set_trace()
# put the local target value to the full target heatmap
# print('==xx.shape:', xx.shape)
local_size = xx.shape[1]
idx_joints = np.tile(np.arange(num_joints)[:, None, None, None],[1, local_size, local_size, local_size])
# print('==idx_joints.shape:', idx_joints.shape)
# print("===np.stack([idx_joints, zz, yy, xx],axis=-1)", np.stack([idx_joints, zz, yy, xx], axis=-1).shape)
idx = np.stack([idx_joints, zz, yy, xx],axis=-1).astype(np.long).reshape(-1, 4)target[idx[:, 0], idx[:, 1], idx[:, 2],idx[:, 3]] = local_target.reshape(-1)
for i in range(num_joints):idx = np.unravel_index(np.argmax(target[i], axis=None), target[i].shape)print('===i, idx:', i, idx)
max_bound = 255
target = target * max_bound
print('==np.max(target):', np.max(target))

3d点坐标: 

3d heatmap最大值索引

三.2d点生成　heatmap


import numpy as np
#x,y是平面坐标系,z是手腕坐标系
joints_3d = np.array([[24.25473, 14.594984, -220.86395],[21.384483, 2.5870495, -102.83917],[2.1389189, 0.4295807, -77.805786],[0.4713831, 4.49901, -45.992554],[24.65406, 7.517185, -131.60638],[20.059254, 10.334126, -121.49127],[14.004571, 31.53947, -106.92682],[0.97307205, 54.702316, -72.0885],[34.38083, 5.5681667, -132.75537],[36.56296, 15.5307255, -122.979614],[34.097603, 38.7413, -104.22839],[23.116486, 59.41091, -62.15027],[40.734467, 13.705656, -126.29144],[48.140816, 5.673216, -115.56366],[52.453285, 28.091465, -97.55463],[41.134747, 46.38981, -56.097656],[38.43096, 12.890821, -117.34686],[44.426872, 1.405302, -101.77527],[50.584797, 10.186543, -84.22754],[255, 255, 51.59436],[0., 0., 0.]], dtype=np.float32)joints_3d_visible = np.array([[1., 1., 1.],[1., 1., 1.],[1., 1., 1.],[1., 1., 1.],[1., 1., 1.],[1., 1., 1.],[1., 1., 1.],[1., 1., 1.],[1., 1., 1.],[1., 1., 1.],[1., 1., 1.],[1., 1., 1.],[1., 1., 1.],[1., 1., 1.],[1., 1., 1.],[1., 1., 1.],[1., 1., 1.],[1., 1., 1.],[1., 1., 1.],[1., 1., 1.],[1., 1., 1.]], dtype=np.float32)img_size = [256, 256]
W, H, D = 64, 64, 64
num_joints = 21
mu_x = joints_3d[:, 0] * W / img_size[0]
mu_y = joints_3d[:, 1] * H / img_size[1]print('==mu_x:', mu_x)
print('==mu_y:', mu_y)target = np.zeros([num_joints, H, W], dtype=np.float32)target_weight = joints_3d_visible[:, 0].astype(np.float32)
# print('==target_weight:', target_weight)
target_weight = target_weight * (mu_x >= 0) * (mu_x < W) * (mu_y >= 0) * (mu_y < H)target_weight = target_weight[:, None]
sigma = 2.5
# only compute the voxel value near the joints location
tmp_size = 3 * sigma# get neighboring voxels coordinates
x = y = np.arange(2 * tmp_size + 1, dtype=np.float32) - tmp_size
yy, xx = np.meshgrid(y, x)xx = xx[None, ...].astype(np.float32)  # (1, 2 * tmp_size + 1, 2 * tmp_size + 1,2 * tmp_size + 1, 2 * tmp_size + 1)
yy = yy[None, ...].astype(np.float32)mu_x = mu_x[..., None, None]  # (21, 1, 1)
mu_y = mu_y[..., None, None]
xx, yy = xx + mu_x, yy + mu_y  # (42, 2 * tmp_size + 1, 2 * tmp_size + 1, 2 * tmp_size + 1)
print('==np.min(xx):', np.min(xx))
print('==np.max(xx):', np.max(xx))
# round the coordinates
xx = xx.round().clip(0, W - 1)
yy = yy.round().clip(0, H - 1)# compute the target value near joints
local_target = np.exp(-((xx - mu_x) ** 2 + (yy - mu_y) ** 2) / (2 * sigma ** 2))
print('==local_target.shape:', local_target.shape)
print('==np.max(local_target):', np.max(local_target))
# import pdb;pdb.set_trace()
# put the local target value to the full target heatmap
local_size = xx.shape[1]
idx_joints = np.tile(np.arange(num_joints)[:, None, None],[1, local_size, local_size])
print('==idx_joints.shape:', idx_joints.shape)
# print("===np.stack([idx_joints, zz, yy, xx],axis=-1)", np.stack([idx_joints, zz, yy, xx], axis=-1).shape)
idx = np.stack([idx_joints, yy, xx], axis=-1).astype(np.long).reshape(-1, 3)target[idx[:, 0], idx[:, 1], idx[:, 2]] = local_target.reshape(-1)
for i in range(num_joints):idx = np.unravel_index(np.argmax(target[i], axis=None), target[i].shape)print('===i, idx:', i, idx)
print(np.max(target))
print(np.min(target))

2d点坐标： 

2d heatmap最大值索引 

 

 

 

本文来自互联网用户投稿，该文观点仅代表作者本人，不代表本站立场。本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如若转载，请注明出处：http://www.mzph.cn/news/493178.shtml

如若内容造成侵权/违法违规/事实不符，请联系多彩编程网进行投诉反馈email:809451989@qq.com，一经查实，立即删除！

相关文章

POP动画[1]

POP动画[1]

POP动画[1] pop动画是facebook扩展CoreAnimation的,使用及其方便:) 1:Spring系列的弹簧效果(两个动画kPOPLayerBounds与kPOPLayerCornerRadius同时运行) #import "RootViewController.h" #import "YXEasing.h" #import "POP.h" #import "YX…
阅读更多...
远比5G发展凶猛！物联网2018白皮书，国内规模已达1.2万亿

远比5G发展凶猛！物联网2018白皮书，国内规模已达1.2万亿

来源&#xff1a;智东西摘要&#xff1a;研判物联网的技术产业进展情况&#xff0c;梳理消费物联网、智慧城市物联网、生产性物联网三类物联网应用现状及驱动因素 。在供给侧和需求侧的双重推动下&#xff0c;物联网进入以基础性行业和规模消费为代表的第三次发展浪潮。 5G、 低…
阅读更多...
收缩分割多边形(PSENet中有使用)

收缩分割多边形(PSENet中有使用)

目的:为了解决密集文本的分割问题 代码: # -*- codingutf-8 -*- import os import cv2 import Polygon as plg import pyclipper import numpy as npdef dist(a, b):return np.sqrt(np.sum((a - b) ** 2))#计算周长 def perimeter(bbox):peri 0.0for i in range(bbox.shape[…
阅读更多...
Android 3D emulation 架构理解

Android 3D emulation 架构理解

Android Emulator 给用户提供 GPU on 选项&#xff0c;意思是利用 Host ( 就是执行 Emulator 的PC机) 的 GPU. 当然PC机必须把 OpenGL 的驱动装好 在实现上就是把 libGLESv1_CM.so libGLESv2.so 替换掉&#xff0c;当system调用 gl的函数的时候&#xff0c;把调用打包为strea…
阅读更多...
年度回顾：2018年的人工智能/机器学习惊喜及预测19年的走势

年度回顾：2018年的人工智能/机器学习惊喜及预测19年的走势

来源&#xff1a;网络大数据考虑到技术变革的速度&#xff0c;我认为让专业IT人士分享他们对2018年最大惊喜及2019年预测的看法会很有趣。以下是他们对人工智能(AI)&#xff0c;机器学习( ML)和其他数据科学迭代的看法&#xff1a;CLARA分析公司首席执行官兼创始人&#xff1a;…
阅读更多...
利用dbnet分割条形码与文字(代码+模型)+知识蒸馏+tensorrt推理+利用pyzbar和zxing进行条形码解析

利用dbnet分割条形码与文字(代码+模型)+知识蒸馏+tensorrt推理+利用pyzbar和zxing进行条形码解析

一.DBnet 1.代码链接 分割条形码与文字代码:github链接:GitHub - zonghaofan/dbnet_torch: you can use dbnet to detect word or bar code,Knowledge Distillation is provided,also python tensorrt inference is provided.&#xff08;提供模型&#xff09; 2.论文阅读 …
阅读更多...
全球值得关注的11家人脸识别公司与机构

全球值得关注的11家人脸识别公司与机构

来源&#xff1a;资本实验室根据美国国家标准与技术研究院&#xff08;NIST&#xff09;的2018年全球人脸识别算法测试&#xff08;FRVT&#xff09;最新结果&#xff0c;今年共有来自全球的39家企业和机构参与本次竞赛。在最新排名中&#xff0c;前五名算法被中国公司包揽&…
阅读更多...
图论基础知识--最小生成树算法kruskal(克鲁斯克尔)和普里姆算法(Prim算法)；最短路径算法Dijkstra(迪杰斯特拉)和Floyd(弗洛伊德)

图论基础知识--最小生成树算法kruskal(克鲁斯克尔)和普里姆算法(Prim算法)；最短路径算法Dijkstra(迪杰斯特拉)和Floyd(弗洛伊德)

一.基础知识 有向图 无向图 以无向图为例: 邻接矩阵: 度矩阵(对角矩阵): 二&#xff0e;最小生成树 应用&#xff1a;将网络顶点看着城市&#xff0c;边看着城市之间通讯网&#xff0c;边的权重看着成本&#xff0c;根据最小生成树可以构建城市之间成本最低的通讯网&#x…
阅读更多...
算法偏见侦探

算法偏见侦探

来源&#xff1a;AI 科技评论摘要&#xff1a;随着越来越多的算法不断渗透入社会的层层面面&#xff0c;如医疗机构、政府部门&#xff0c;对算法偏见的讨论越来越多。这个月&#xff0c;Nature 杂志评选出 2018 年最受欢迎的十大科学长篇专题报道&#xff0c;其中&#xff0c;…
阅读更多...
pytorch实现常用的一些即插即用模块(长期更新)

pytorch实现常用的一些即插即用模块(长期更新)

1.可分离卷积 #coding:utf-8 import torch.nn as nnclass DWConv(nn.Module):def __init__(self, in_plane, out_plane):super(DWConv, self).__init__()self.depth_conv nn.Conv2d(in_channelsin_plane,out_channelsin_plane,kernel_size3,stride1,padding1,groupsin_plane)…
阅读更多...
硅片行业：过剩背景下的寡头市场

硅片行业：过剩背景下的寡头市场

来源&#xff1a;乐晴智库精选▌竞争格局:过剩背景下的寡头市场&#xff0c;规模壁垒初步形成光伏产业总体处于产能过剩的状态&#xff0c;硅片环节的过剩尤为突出。根据PVInfolink的统计数据&#xff0c;截至2018年2季度末&#xff0c;全球硅片总产能超过160GW&#xff0c;年化…
阅读更多...
从attention到Transformer+CV中的self-attention

从attention到Transformer+CV中的self-attention

一.总体结构 由于rnn等循环神经网络有时序依赖&#xff0c;导致无法并行计算&#xff0c;而Transformer主体框架是一个encoder-decoder结构&#xff0c;去掉了RNN序列结构&#xff0c;完全基于attention和全连接。同时为了弥补词与词之间时序信息&#xff0c;将词位置embedding…
阅读更多...
12年后，人工智能和人类会是什么样？这是900位专家的看法|报告

12年后，人工智能和人类会是什么样？这是900位专家的看法|报告

来源&#xff1a;机器之能摘要&#xff1a;有分析师预计&#xff0c;到2030年&#xff0c;在复杂的数字系统中&#xff0c;人们将更加依赖于网络人工智能。 有人说&#xff0c;随着对这些网络工具的广泛使用&#xff0c;我们将继续沿着历史的轨迹生活地更好。也有一些人说&…
阅读更多...
水印去除(基于nosie2noise优化 代码+模型)

水印去除(基于nosie2noise优化 代码+模型)

github链接 1.感受野计算: :本层感受野; :上层感受野; :第i层卷积或池化的步长 k:本层卷积核大小 2.空洞卷积卷积核计算:Kk(k-1)(r-1)&#xff0c;k为原始卷积核大小&#xff0c;r为空洞卷积参数空洞率&#xff0c;带入上式即可计算空洞卷积感受野&#xff1b; 3.针对noi…
阅读更多...
广度深度都要，亚马逊是如何推动 Alexa 内生成长的？

广度深度都要，亚马逊是如何推动 Alexa 内生成长的？

来源&#xff1a;雷锋网摘要&#xff1a;发展到今天&#xff0c;Alexa 已经成为亚马逊旗下最重要的几个业务支柱之一&#xff0c;尤其是在人工智能语音助手层面&#xff0c;它和 Google Assistant、Apple Siri、Microsoft Cortana 并驾齐驱&#xff0c;甚至在应用场景上有领先之…
阅读更多...
剖析云平台中的“共享型数据库”

剖析云平台中的“共享型数据库”

剖析云计 算中的“共享型数据库” 摘要&#xff1a; 随着云计算的出现&#xff0c;出现了很多新的名词&#xff0c;像云数据库、云存储、弹性扩容&#xff0c;资源隔离等词汇。下面就大家炒的比较热的“共享型数据库”做一下解释&#xff0c;给大家剖析什么叫“共享型数据库”。…
阅读更多...
FCOS: A Simple and Strong Anchor-free Object Detector

FCOS: A Simple and Strong Anchor-free Object Detector

论文链接 一.背景 1.anchor-base缺点　　　　　　　　　 (&#xff11;)&#xff0e;anchor的设置对结果影响很大,不同项目这些超参都需要根据经验来确定&#xff0c;难度较大&#xff0e; (&#xff12;)&#xff0e;anchor太过密集&#xff0c;其中很多是负样本&#xff…
阅读更多...
大数据有十大应用领域，看看你用到了哪个？

大数据有十大应用领域，看看你用到了哪个？

来源&#xff1a;网络大数据摘要&#xff1a;如果提到“大数据”时&#xff0c;你会想到什么?也许大部分人会联想到庞大的服务器集群;或者联想到销售商提供的一些个性化的推荐和建议。如今大数据的深度和广度远不止这些&#xff0c;大数据已经在人类社会实践中发挥着巨大的优势…
阅读更多...
2018年《环球科学》十大科学新闻出炉：霍金逝世、贺建奎事件位列前二

2018年《环球科学》十大科学新闻出炉：霍金逝世、贺建奎事件位列前二

来源&#xff1a;量子位如果要用两个词来定义2018年的话&#xff0c;我们可能会选择“进步”与“反思”。中国科学在持续进步&#xff0c;克隆猴“中中”与“华华”、单条染色体的酵母&#xff0c;都是世界级的研究成果。“火星快车”在火星上发现大面积的液态湖泊&#xff0c;…
阅读更多...
CornerNet: Detecting Objects as Paired Keypoints

CornerNet: Detecting Objects as Paired Keypoints

CornerNet论文链接 Hourglass Network论文链接 一.背景 1.anchor-base缺点　　　　　　　　　 (&#xff11;)&#xff0e;anchor的设置对结果影响很大,不同项目这些超参都需要根据经验来确定&#xff0c;难度较大&#xff0e; (&#xff12;)&#xff0e;anchor太过密集&…
阅读更多...
推荐文章
最新文章

Copyright @ 2022~2023