Comments (7)
from onnx2tflite.
It's seem a new pattern of PRelu. Your onnx model version is 16, can you provide model file to me or fix it by yourself.
from onnx2tflite.
It's seem a new pattern of PRelu. Your onnx model version is 16, can you provide model file to me or fix it by yourself.
我可以将onnx模型提供给您,我也可以先将onnx版本降低到多少再试试呢?
from onnx2tflite.
链接: https://pan.baidu.com/s/1ksZcbMwm5v8N5JqVGgmdvQ?pwd=t7jw 提取码: t7jw
--来自百度网盘超级会员v3的分享
from onnx2tflite.
链接: https://pan.baidu.com/s/1ksZcbMwm5v8N5JqVGgmdvQ?pwd=t7jw 提取码: t7jw --来自百度网盘超级会员v3的分享
onnx模型链接地址在这里,我先从mxnet转换为onnx的,转换脚本如下:
import mxnet as mx
import numpy as np
import onnx
print('mxnet version:', mx.__version__)
print('onnx version:', onnx.__version__)
from mxnet.contrib import onnx as onnx_mxnet
from onnx import checker
syms = './mxnet_models/arcface/model-symbol.json'
params = './mxnet_models/arcface/model-0000.params'
input_shape = (1, 3, 112, 112)
onnx_file = './models/arcface_onnx131.onnx'
converted_model_path = onnx_mxnet.export_model(syms, params, [input_shape], np.float32, onnx_file)
model_proto = onnx.load_model(converted_model_path)
checker.check_graph(model_proto.graph)
from onnx2tflite.
It's fixed, please pull latest code.
from onnx2tflite.
@MPolaris Thank you!
from onnx2tflite.
Related Issues (20)
- large difference after adding SE module HOT 1
- ValueError HOT 1
- Convert onnx with dynamic input shape HOT 2
- run torchvision_test, got KeyError: 'Shape not implemented yet' HOT 6
- 尝试把IMDN和RFDN的PyTorch模型转换成.tflite文件,使用AI benchmark APP简单部署在安卓手机测试速度,失败了!!! HOT 4
- KeyError: 'NonMaxSuppression not implemented yet' (YOLOv7 tiny onnx to tflite) HOT 2
- Dimensional error HOT 3
- Add option to allow for dynamic resize HOT 4
- ValueError: Layer p_re_lu weight shape (1, 1, 32) is not compatible with provided weight shape (32, 1, 1). HOT 3
- Extract score and class_id from converted model HOT 6
- Add setup.py to be installed as a package HOT 2
- Opencv resize method use different axises, which leads to errors during int8 callibration
- onnx converting to tflite got an error, is there any solutions? HOT 3
- max error is too big during conversion HOT 2
- dimension error
- 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
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.