Comments (7)
不是的,lite可以支持2d3d4d的各种输入,多输入什么都可以 你这是不是设置mean和std啥的了
from rknn-toolkit2.
@yuyun2000 感谢回复!我训练、转换和部署的过程如下。
- 数据集如下格式
- 通过tensorflow训练并转换为tflite格式
model = tf.keras.Sequential([tf.keras.layers.Dense(10, input_shape=(3,), activation='relu'), tf.keras.layers.Dense(1)])
model.compile(optimizer='adam', loss='mse' )
model.fit(x, y, epochs=500)
converter = tf.lite.TFLiteConverter.from_keras_model(model)
tflite_model = converter.convert()
with open('advertising_model.tflite', 'wb') as f:
f.write(tflite_model)
- 转换模型成功
import numpy as np
import pandas as pd
from rknn.api import RKNN
import matplotlib.pyplot as plt
rknn = RKNN(verbose=True)
# Pre-process config
print('--> Config model')
rknn.config(target_platform='rk3588')
print('done')
# Load model
print('--> Loading model')
ret = rknn.load_tflite(model='advertising_model.tflite')
if ret != 0:
print('Load model failed!')
exit(ret)
print('done')
# Build model
print('--> Building model')
ret = rknn.build(do_quantization=False)
if ret != 0:
print('Build model failed!')
exit(ret)
print('done')
# Export rknn model
print('--> Export rknn model')
ret = rknn.export_rknn('./advertising_model.rknn')
if ret != 0:
print('Export rknn model failed!')
exit(ret)
print('done')
- 部署到rk3588板上无法正常推理。
import numpy as np
import pandas as pd
from rknnlite.api import RKNNLite
rknn_model = "advertising_model.rknn"
rknn_lite = RKNNLite(verbose=True)
print('--> Load RKNN model')
ret = rknn_lite.load_rknn(rknn_model)
if ret != 0:
print('Load RKNN model failed')
exit(ret)
print('done')
ret = rknn_lite.init_runtime(core_mask=RKNNLite.NPU_CORE_AUTO)
if ret != 0:
print('Init runtime environment failed!')
exit(ret)
print('done')
feature = np.array([24.1, 30.0, 51.0])
quantized_feature = np.round(feature).astype(np.float16)
input_data = quantized_feature.reshape(1, -1)
data_format = 'nhwc'
inputs_pass_throught = [0]
output = rknn_lite.inference(inputs=[input_data], data_format=data_format, inputs_pass_through=inputs_pass_throught)
print(output)
期间日志信息如帖子主题图片中所述。
无论如何修改feature的值,output输出始终为[array([[1.1279297]], dtype=float32)]
没有头绪!!!请求帮助!
from rknn-toolkit2.
可不可以先尝试连接板子到rknntoolkit,用toolkit的inference接口进行推理,看看结果? 参考这个代码可以连板推理:https://github.com/yuyun2000/rkan/blob/main/rk/infer.py
from rknn-toolkit2.
@yuyun2000
尝试了在PC上使用rknn-toolkit2连接RK3588进行推理。结果如下:
任意输入推理出的结果都是1.09。
from rknn-toolkit2.
看见你的版本落后于最新版本很多,不如先更新一下版本?
from rknn-toolkit2.
好的,我尝试下新版本。
from rknn-toolkit2.
这个不是报错,这个是说输入是1,2,4通道的4维数据(也就是argb格式的数据)时NPU可以对输入进行减均值除方差操作,而在其它情况下这个工作需要CPU来做。造成的结果就是速度会慢一点点。这不是问题的根源。
from rknn-toolkit2.
Related Issues (20)
- [Bug report] Failed to config layer: 'Conv:/lila2/conv/conv/Conv', Fatal Error HOT 12
- ShapeInferenceError when converting to rknn model
- 是否有计划支持更大转置算子,或者有没有优化方法 HOT 2
- 想咨询一下,RK3562的NPU是否支持,并行推理多个不同的模型
- NDK build ERROR HOT 1
- illegal instruction (core dumped) HOT 1
- 真服了写的跟屎一样 HOT 2
- movenet rknn infer failed HOT 6
- Add YOLO object tracking feature
- 3588推理模型时报错failed to submit! HOT 1
- 是否支持EVA-CLIP系列模型部署 HOT 1
- Yolov5s转成rknn部署到rv1106精度降低
- 模型初始化错误 HOT 1
- main.cc 里面的rknn_init 报错 segmentation fault HOT 7
- failed to submit!, op id: 1, op name: exLSTM:/rnn/LSTM,
- can we deploy Faster RCNN on Rock 3588 NPU? HOT 5
- rknn_yolov5_demo使用自己训练的模型时出错
- 模型转换cos相似度为1.0或0.999,但是欧式距离euc非常高,该怎么解决 HOT 2
- RKNN-Toolkit2 inference segmentation fault/return None
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 rknn-toolkit2.