共85个项目结果
热搜:
Feijiang
Mofang
Kedaxunfei

图像分辨率增强 Python Star 3

  • 该模型对图像分辨率进行四倍上采样增强,以生成照片般逼真的细节。宽/高最多放大至2000像素。如果原图宽/高超过2000像素,则保持不变。
  • 浏览量:1903 下载量:38 about 1 month前

    千种物体识别 Python Star 3

  • 该模型基于ImageNet 2012大规模视觉识别挑战中的1000种不同类别的对象数据训练而成,由卷积神经网络构成,该网络使用Inception-ResNet-v2架构。模型输入299x299图像,输出是估计结果和概率的列表。
  • 浏览量:1619 下载量:180 about 1 month前

    手写数字识别 Python Star 3

  • 该模型基于卷积神经网络(CNN)实现手写数字识别,使用Keras框架实现,识别正确率为95%左右。
  • 浏览量:2017 下载量:525 about 1 month前

    中文语音相似度判别 Python Star 3

  • 提供了一种通过语音索引汉字的算法。 给定两个相同长度的中文单词,模型确定两个单词之间的距离,并返回几个与给定单词接近的候选单词。 该规范符合ISO 7098:2015中定义的罗马化指导的普通话语音原则。
  • 浏览量:1607 下载量:781 about 1 month前

    二维码生成和识别 Python Star 4

  • 将文本字符串转换成二维码图片;识别二维码图片还原成原始文字。
  • 浏览量:1630 下载量:539 about 1 month前

    汉字转拼音 Python Star 3

  • 把一句话中的汉字转换成汉语拼音。
  • 浏览量:1199 下载量:425 about 1 month前

    papers C++ Star 0

  • papers
  • 浏览量:1847 下载量:323 about 1 month前

    Real-Time-Crop-Recognition Python Star 0

  • Real-time crop recognition in transplanted fields with prominent weed growth: a visual-attention-based approach
  • 浏览量:1907 下载量:774 about 1 month前

    DEMO code for Deep Bit Depth Expansion Python Star 1

  • Demo code (MXNET) for: Deep reconstruction of least significant bits for bit-depth expansion --------------------------------- Abstract: Bit-depth expansion (BDE) is important for displaying a low bit-depth image in a high bit-depth monitor. Current BDE algorithms often utilize traditional methods to fill the missing least significant bits and suffer from multiple kinds of perceivable artifacts. In this paper, we present a deep residual network-based method for BDE. Based on the different properties of flat and non-flat areas, two channels are proposed to reconstruct these two kinds of areas, respectively. Moreover, a simple yet efficient local adaptive adjustment preprocessing is presented in the flat-area-channel. By combining the benefits of both the traditional debanding strategy and network-based reconstruction, the proposed method can further promote the subjective quality of the flat area. Experimental results on several image sets demonstrate that the proposed BDE network can obtain favorable visual quality as well as decent quantitative performance.
  • 浏览量:1304 下载量:458 2 months前

    test Python Star 0

  • test
  • 浏览量:1109 下载量:548 2 months前

    ihub@pcl.ac.cn 鹏城实验室人工智能研究中心

    版权所有:鹏城实验室    粤ICP备18066427号-6    Powerd by 国防科技大学Trustie