Richard-coder

# 平台(如果交叉编译请再附上交叉编译目标平台): # ubuntu x86 cpu: # Github版本: # Github Version: 1.2和 master， master 的commit id 是 344629419f710b39559e616f1af7bb7bd29617db # 编译方式: # Compiling cmake tensorflow模型转为mnn格式，用fastTestTf.py工具测试是success，但是用c++跑每次结果都不一样 因为模型是tf 1.6写的，所以我对fastTestTf.py脚本做了一些修改，对结果没影响 模型地址 链接：https://pan.baidu.com/s/11Eip1A2kRamT4n_G5q40dA 提取码：9i0g c++测试代码...

ubuntu, x86, c++， tnnproto格式的模型在执行推理时 crash 在 softmax层处, 但是用python执行onnx格式的模型没问题。

4

**1. 环境（environment）** - Build OS and Version: Ubuntu - RunTime OS Version: Linux - RunTime DEVICE: x86 **2. Github版本** - branch：v3.0 - commit(optional): **3. 编译方式(compile method)** build_linux_native.脚本编译的，debug模式 **4. 编译日志(build log)**...

I can only download the dataset used in the paper co-fusion, where can I download the dataset used in maskfusion , such as skateboards and teddy bears

Question about load and render Wavefront OBJ with multi textures？

1

I have a Wavefront OBJ model with two texttures, like following. ```bash Model.mtl Model.obj Model0_0000.png Model1_0000.png ``` I can load the model successfully, but while I try to render the...