Comments (4)
这是IMDN的github仓库
https://github.com/Zheng222/IMDN
from onnx2tflite.
工具只负责模型转换和简单的校验功能哦。
首先在最后工具报了Warning,转换是成功了,但是模型运行失败了,需要自己检查是哪里的问题。
你可以检查是否生成了tflite文件,使用netron查看。
然后使用tf.lite.Interpreter
来检查模型是否能正确加载和推理。
其次不同版本的tensorflow也会导致推理失败哦,比如组卷积支持度的问题。
from onnx2tflite.
我发现了问题所在:
1.这份代码(或者说Tensorflow2.5,tflite)不支持这个超分辨率常用的操作,pixel_shuffle = nn.PixelShuffle(upscale_factor),删除后得到的.tflite文件在AI benchmark APP就可以run。这一处,需要将这个函数用DepthToSpace来替换
2.这份代码不支持GELU激活函数,改成Leaky ReLU函数即可
from onnx2tflite.
- 在ONNX中,对应nn.PixelShuffle的操作是DepthToSpace算子,而onnx2tflite是支持这个算子的(layers/deformation_layers.py#179),你应该检查torch.onnx.export的ONNX算子是否正确映射了该算子。
- 你可以在layers/activations_layers.py中自行实现GELU激活函数,非常简单。
from onnx2tflite.
Related Issues (20)
- Convert fail Cannot reshape a tensor HOT 1
- yolov5s.onnx转换tflite出错 HOT 2
- Unable to perform 1dconv conversion? HOT 1
- The gpu cannot be used after model conversion HOT 1
- onnx转为tflite 为啥数据类型变成了uint8? HOT 1
- 模型转换缺少conv3d算子 HOT 3
- 报错
- 模型转换报错 HOT 2
- onnx转tflite 如何让维度保持不变 HOT 1
- ValueError: Unrecognized keyword arguments passed to Conv2D: {'weights': [array([[[[-0.16197614, HOT 6
- weight value errot HOT 1
- 可以在转换的时候做fp16量化吗 HOT 2
- ValueError: Unrecognized keyword arguments passed to Conv2D: {'weights': [array([[[[-2.05928516e-02, -1.33914594e-02, -1.65286055e-03, ..., HOT 3
- 转换报错 'tuple' object has no attribute 'ndims' HOT 1
- Feature Request: NonMaxSuppression Layer HOT 1
- 转换onnx模型失败 HOT 1
- 转换后误差大,而且无法进行推理 HOT 2
- 用了博主说的官方onnx-tf和这个onnx2tflite做了yolox_tiny的对比 HOT 1
- KeyError:'GRU not implemented yet'
- 运行报错 HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from onnx2tflite.