惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

G
GRAHAM CLULEY
T
Tenable Blog
Know Your Adversary
Know Your Adversary
C
CXSECURITY Database RSS Feed - CXSecurity.com
P
Privacy International News Feed
S
Security Affairs
NISL@THU
NISL@THU
O
OpenAI News
Attack and Defense Labs
Attack and Defense Labs
Application and Cybersecurity Blog
Application and Cybersecurity Blog
Hacker News: Ask HN
Hacker News: Ask HN
Webroot Blog
Webroot Blog
Schneier on Security
Schneier on Security
S
SegmentFault 最新的问题
S
Schneier on Security
G
Google Developers Blog
V
V2EX
C
Check Point Blog
U
Unit 42
Google DeepMind News
Google DeepMind News
T
Threatpost
阮一峰的网络日志
阮一峰的网络日志
T
The Exploit Database - CXSecurity.com
Recent Announcements
Recent Announcements
M
MIT News - Artificial intelligence
S
Secure Thoughts
博客园 - 司徒正美
Recorded Future
Recorded Future
P
Proofpoint News Feed
Spread Privacy
Spread Privacy
K
Kaspersky official blog
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
AI
AI
博客园 - 聂微东
N
News and Events Feed by Topic
SecWiki News
SecWiki News
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
V
Vulnerabilities – Threatpost
P
Palo Alto Networks Blog
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
Engineering at Meta
Engineering at Meta
Recent Commits to openclaw:main
Recent Commits to openclaw:main
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
酷 壳 – CoolShell
酷 壳 – CoolShell
WordPress大学
WordPress大学
The Hacker News
The Hacker News
The Last Watchdog
The Last Watchdog
Project Zero
Project Zero
W
WeLiveSecurity
博客园 - Franky

博客园 - 无左无右

mmdetection3d-1.0.0rc0 安裝 左乘和右乘,行向量和列向量 grep -rl "math\.tan" /media/data_1/everyday/2025_down --include="*.py" - 无左无右 已知相机到车的rt 4x4矩阵,求pitch和yaw角度 torch.where(condition, x, y) 是一个三元运算符:如果条件为真,取 x 的值;如果条件为假,保持 y(即原本的 weights)不变。 for decoder_idx, (cls, reg) in enumerate(zip(cls_scores, reg_preds)): 左乘与右乘 GridMask--随机用“网格状”的遮挡去盖住图片的一部分,迫使模型学习更鲁棒的特征。 obtain_sensor2top函数, sensor → ego_s → global → ego_lidar → lidar assert osp.exists(self.table_root), 'Database version not found: {}'.format(self.table_root) Deformable-DETR 网页绘图,无需注册 value = value.masked_fill(input_padding_mask[..., None], float(0)) DETR 点云绕不同的轴旋转可视化,roll,pitch,yaw 相机坐标系转车辆坐标系以及相反, RT矩阵,旋转变换P_cam = rot_car2cam * P_car + trans_car2cam; P_cam = rot * (P_car - trans) 连续200帧的ego的RT矩阵R_prevel2wld,shape是[200,4,4],目标的rt矩阵的R_curpt2curvels的shape是[87, 200, 4, 4], 87是目标数量, 把t11时刻的目标对齐到t0, numpy实现 vscode launch.json debug 带caffe库的工程代码 标注工具--抹除目标 ubuntu1804安装 mmdet3d 0.17.1 报错与解决 np.stack(a,axis=x), x=0,1,2 外参扰动 car_noise2cam = car2cam @ car_noise2car BEVDet-net部分 TP, FP, precision, recall bevdepth- 数据处理部分 ubuntu 硬盘挂载,重启后硬盘掉了 create_frustum 分析 (frustum = torch.stack((x_coords, y_coords, d_coords, paddings), -1)) sweep_lidar_depth = sweep_lidar_depth.reshape(batch_size * num_cams, *sweep_lidar_depth.shape[2:]) torch.where(condition, x, y) 自动驾驶,单目3D中的alpha角度
log_str += ', '.join(log_items)
无左无右 · 2026-05-19 · via 博客园 - 无左无右

log_str += ', '.join(log_items)
这行是 Python 里很常见的 字符串拼接 + join 语法,拆开看其实很简单。
用 ", " 作为分隔符,把 list 里的字符串拼成一个长字符串

log_items = ["loss: 1.0", "lr: 0.001", "time: 0.5"]

result = ', '.join(log_items)
#loss: 1.0, lr: 0.001, time: 0.5
log_items = []
        for name, val in log_dict.items():
            # TODO: resolve this hack
            # these items have been in log_str
            if name in [
                    'mode', 'Epoch', 'iter', 'lr', 'time', 'data_time',
                    'memory', 'epoch'
            ]:
                continue
            if isinstance(val, float):
                val = f'{val:.4f}'
            log_items.append(f'{name}: {val}')
        log_str += ', '.join(log_items)

2026-05-19 20:45:13,430 - mmdet - INFO - Epoch [1][150/27015] lr: 1.064e-04, eta: 67 days, 19:02:59, time: 1.130, data_time: 0.017, memory: 8456, loss_cls_0: 1.6042, loss_reg_0: 2.1852, loss_cls_1: 1.5532, loss_reg_1: 2.2024, loss_cls_2: 1.5287, loss_reg_2: 2.1910, loss_cls_3: 1.5370, loss_reg_3: 2.1937, loss_cls_4: 1.5375, loss_reg_4: 2.2282, loss_cls_5: 1.5239, loss_reg_5: 2.2710, loss_depth: 1.3339, loss: 23.8899, grad_norm: 104.1702

图片