-
I‘ve trained my yolo as your demo,but the kmodel cant run continuously,as it says RAM not enough.但是我把yolo变小（把卷积核调小）后，会卡死在kpu.run_yolo2这一步，五六分钟都没有输出结果。请问是我训练出错了吗
-
Ideas:
- Specify port types. Perhaps ports can be one of `kModel`, `kRender`, or `kRaster`
- Model ports are for model data (verts, UVs, etc.)
- Render ports have backwards-facing attributes …
-
I’m reaching out to report an issue with image generation when using a custom 164 MB Lora that I created with Replicate, in conjunction with the Flux model. The generation time is significantly longer…
-
System Specs: 3080 10G with 32gb RAM
This is potentially an issue to low VRAM, and system not freeing up enough memory before next generation. But can't say for sure,
Logs for debugging:
```pow…
-
尝试MaixHub上的模型训练，简单用了三个模型，按教程用MaixBit采集图片，上传训练，一起顺利，只是遇到点小困惑：其中两个标签交换了，确定不是我图片文件夹名称错所致。
在尝试修改标签时，发现所提供的程序根本没有使用输出结果中的标签文件 Labels.txt
尝试修改程序，发现标签文档格式不太合理，原始输出的内容是：
labels = ["SDCard", "cover", "p…
-
# Option to use the order of nodes in which it is defined on model
**SPMeta2 CSOM Standard 1.2.120**
Maybe it could be a great option somehow to let the developers not to use the default order o…
-
你好，zhen！
训练自己数据集，模型：mobile_yolo_v1 （0.75），得到的h5模型测试效果良好，可是部署到k210上，屏幕识别画出一堆乱框。
同样的代码和流程，烧录官网给出的example，mobile_yolo的识别20类物体的kmodel，在k210上可以正常运行，屏幕显示也正常。
请教一下，产生这个乱框问题的可能原因是什么？
-
您好，我通过该项目训练自己的数据集，得到了h5，tflite，kmodel三种模型，并通过netron大致了解了h5和tflite的网络架构。
我想尝试着用Pytorch完成这一项目，按照h5和tflite重新定义网络结构，但是无法使用预训练模型。
作者能分享一下这个项目的大致实现过程吗？可以参考一下。
-
first thought i wanted to rename `other_args` to something specific to `metab_Kmodel`, because that's silly to have such a generically named argument that applies to just one model.
but then maybe t…
-
Hi, I have a number of TFLITE models that I have trained for a specific image classification task, and they run well on the Maix Dock board. I have used ncc to compile them into Kmodel files for use w…