摘要：$ cat draw_bbox.py import os import cv2 label_dir = "./resize_label/" image_dir = "./resize_img/" for image in os.listdir(image_dir): #print(image) im
阅读全文
摘要：# cat resize_label_640_480_PIL.py import os import cv2 #import pandas as pd w = 640 h = 480 images = "./images/" for next_image in os.listdir(images):
阅读全文
摘要：#!/usr/bin/env python # -*- coding: utf-8 -*- import os import shutil image_root = "./train2017" label_root = "./labels" no_label = "./no_label" image
阅读全文
摘要：image_cnt=0 class SSDDataAugmentation: def __init__(self, img_height=300, img_width=300, background=(123, 117, 104), labels_format={'class_id': 0, 'xm
阅读全文
摘要：From my experience with tensorflow and keras (which is confirmed by this article): https://medium.com/mini-distill/effect-of-batch-size-on-training-dy
阅读全文
摘要：'zooming out' (image gets rendered smaller than the canvas) 1)https://www.youtube.com/watch?v=q3B4ohFHe7E Video shows what zoom out means. To focus a
阅读全文
摘要：https://stackoverflow.com/questions/53012856/what-is-an-object-detection-head In some domains, head is a term for the start or the beginning of someth
阅读全文
摘要：https://blog.csdn.net/m0_37644085/article/details/81948396 https://blog.csdn.net/u012609509/article/details/88680841
阅读全文
摘要：https://github.com/AgaMiko/data-augmentation-review
阅读全文
摘要：https://awesomeopensource.com/project/MarvinTeichmann/KittiSeg
阅读全文
摘要：https://docs.nvidia.com/deeplearning/frameworks/user-guide/index.html https://docs.nvidia.com/ngc/ngc-user-guide/ https://docs.nvidia.com/ngc/ngc-intr
阅读全文
摘要：https://machinelearningmastery.com/using-learning-rate-schedules-deep-learning-models-python-keras/ https://machinelearningmastery.com/difference-betw
阅读全文
摘要：From https://machinelearningmastery.com/difference-between-a-batch-and-an-epoch/ What Is the Difference Between Batch and Epoch? The batch size is a n
阅读全文
摘要：转自 https://www.jianshu.com/p/fbb96bb49782 准确率(Accuracy), 精确率(Precision), 召回率(Recall) 和 F1-Measure 举个栗子：假设我们手上有60个正样本，40个负样本，我们要找出所有的正样本，系统查找出50个，其中只有4
阅读全文
摘要：ByteDance open sourcing distributed training framework BytePS https://github.com/bytedance/byteps BytePS is a high performance and general distributed
阅读全文
摘要：https://www.deeplearning.ai/blog/working-ai-at-the-office-with-vp-of-applied-deep-learning-research-bryan-catanzaro/?utm_source=social&utm_medium=twit
阅读全文
摘要：https://www.cnblogs.com/zf-blog/p/6734686.html AUC和MAP之间的联系： AUC主要考察模型对正样本以及负样本的覆盖能力（即“找的全”），而MAP主要考察模型对正样本的覆盖能力以及识别能力（即对正样本的“找的全”和“找的对”） 深入理解AUC http
阅读全文
摘要：https://github.com/DigitalSlideArchive/HistomicsTK https://blog.kitware.com/cell-nuclei-detection-on-whole-slide-histopathology-images-using-histomics
阅读全文
摘要：https://venturebeat.com/category/ai/
阅读全文
浙公网安备 33010602011771号