GLTF代表Graphics Language Transmission Format（图形语言传输格式）。这种跨平台格式已成为Web上的3D对象标准。它由OpenGL和Vulkan背后的3D图形标准组织Khronos所定义，这使得GLTF基本上成为3D模型的JPG格式：Web导出的通用标准。

Convolutional Neural Networks (CNNs) are computationally intensive, which limits their application on mobile devices. Their energy is dominated by the number of multiplies needed to perform the convolutions. Winograd’s minimal filtering algorithm and network pruning can reduce the operation count, but these two methods cannot be straightforwardly combined — applying the Winograd transform fills in the sparsity in both the weights and the activations. We propose two modifications to Winograd-based CNNs to enable these methods to exploit sparsity.

用于tensorboard打开的可视化模型

opencv4.5新更新的TextRecognitionModel和TextDetectionModel_DB的onnx模型文件，包含DB_TD500_resnet18.onnx，DB_TD500_resnet50.onnx，crnn_cs_CN.onnx和alphabet_3944.txt

1.在Unity中制作好地形； 2.选中场景中的地形，点击Tools菜单下的地形导出即可； 3.导出的地形是obj格式。

（亲测可用）tensorflow训练模型进行调参，生成inception_v1.pb模型文件用于预测

pkuseg 中文分词模型包

演示了Wpf动态加载Xaml的3D模型文件，并实现3D模型的旋转、移动、放大等，适合Wpf进行3D开发的人学习和参考

用pb文件，输入input，修改output_node,可以输出神经网络每层的输出features

一个简单的OSG加载地形文件，还同时提供两个模型