摘要：
Filters and Convolutions Excerpt from Focal Loss Classification Subnet: The classification subnet predicts the probability of object presence at each 阅读全文
摘要：
Faster-RCNN and RPN Contribution RPN predefined bboxes(anchors) with different scales The rest is inherited from Fast RCNN RPN learns the proposals fr 阅读全文
摘要：
RCNN, Fast-RCNN, Faster-RCNN TL;DR ref https://blog.paperspace.com/faster-r-cnn-explained-object-detection/ progress RCNN: Two Stage selective search 阅读全文
摘要：
import os import sys BASE = os.path.join(os.path.dirname('D:/Data/Documents/Blog/pyblog/scripts/python/renderer/__configs.py'), '../../../') print(BAS 阅读全文
摘要：
Linux 按照文件名找到所有Python 进程并且结束 pkill -9 -f XXX(Pattern) https://stackoverflow.com/questions/8987037/how-to-kill-all-processes-with-a-given-partial-name 阅读全文
摘要：
右键，导出成为.rdf格式 选择File-Import，选择 就可以导入一整个文件夹了 阅读全文
摘要：
可以采用翻译软件翻译 Temporal RoI Align for Video Object Recognition TL;DR Goal: exploit temporal information for the same object instance in a video. RPN -> pr 阅读全文
摘要：
https://about.gitlab.com/handbook/markdown-guide/ 阅读全文
摘要：
https://docs.wandb.ai/guides/track/advanced/distributed-training def is_dist_avail_and_initialized(): if not dist.is_available(): return False if not 阅读全文
摘要：
关闭keyboard shortcut markdown.extension.onBackspaceKey即可 阅读全文