Selected article for: "batch size and CT volume"
Author: Chuansheng Zheng; Xianbo Deng; Qing Fu; Qiang Zhou; Jiapei Feng; Hui Ma; Wenyu Liu; Xinggang Wang
Title: Deep Learning-based Detection for COVID-19 from Chest CT using Weak Label
  • Document date: 2020_3_17
    • ID: ll4rxd9p_19
    Snippet: Training and Testing Procedures The DeCoVNet software was developed based on the PyTorch framework [21] . Our proposed DeCoVNet was trained in an end-to-end manner, which meant that the CT volumes were provided as input and only the final output was supervised without any manual intervention. The network was trained for 100 epochs using Adam optimizer [22] with a constant learning rate of 1e-5. Because the length of CT volume of each patient was .....
    Document: Training and Testing Procedures The DeCoVNet software was developed based on the PyTorch framework [21] . Our proposed DeCoVNet was trained in an end-to-end manner, which meant that the CT volumes were provided as input and only the final output was supervised without any manual intervention. The network was trained for 100 epochs using Adam optimizer [22] with a constant learning rate of 1e-5. Because the length of CT volume of each patient was not fixed, the batch size was set to 1. The binary cross-entropy loss function was used to calculate the loss between predictions and ground-truth labels.

    Search related documents:
    Co phrase search for related documents
    • CT volume and loss function: 1
    • CT volume and patient CT volume: 1, 2, 3, 4, 5
    • CT volume and patient CT volume length: 1
    • end end and final output: 1
    • end end and ground truth: 1, 2, 3, 4, 5, 6
    • end end and input provide: 1
    • end end and loss function: 1, 2, 3, 4, 5, 6
    • end end and manual intervention: 1
    • ground truth and learning rate: 1, 2
    • ground truth and loss function: 1, 2, 3, 4, 5, 6
    • ground truth and patient CT volume: 1
    • ground truth prediction and loss function: 1
    • ground truth prediction label and loss function: 1
    • learning rate and loss function: 1, 2, 3, 4, 5, 6, 7
    • learning rate and PyTorch framework: 1
    • loss function and manual intervention: 1
    • loss function and PyTorch framework: 1