Comments (7)
Ok, you saved me... My bad!
I did not compile the model.
I only converted it to .tflite and I was assuming that this was the compile step.
Thank you for your help.
I'm closing the issue.
from edgetpu.
@aaguiar96 Can you give some code snippets, as well as models used? It's a little hard to tell with the given info, but yes, most inference works will be delegated to the TPU (depending on the model). Keep in mind that input processing will be executed with the CPU.
Edit: Also some data transferring should be using CPU
from edgetpu.
My main question is:
- If I use the
detection engine
for example as:
engine = new coral::DetectionEngine((*params).model);
input_tensor_shape = (*engine).get_input_tensor_shape();
labels = coral::ReadLabelFile((*params).labels);
...
std::vector<uint8_t> input_tensor = coral::GetInputFromImage(in_image, {input_tensor_shape[1], input_tensor_shape[2], input_tensor_shape[3]});
auto results = (*engine).DetectWithInputTensor(input_tensor);
will this code be delegated to the USB Accelerator device?
I'm using a retrained MobileNet model, compatible with the edgetpu
.
Thanks in advance.
from edgetpu.
@aaguiar96 Hi, as far as I could tell, the code looks okay at glance. As for your retrained model, have you compiled it for the edgetpu
? And could you also confirm that it is indeed using CPU with htop?
from edgetpu.
Yes, it is compiled for the edgetpu
.
So, this code should been working? I profiled the code and the Invoke()
routine in RunInference()
function is the one who is responsible for the major CPU occupation.
I think this should not occur if the detection is running on the coral device.
Am I wrong?
from edgetpu.
Hi, you're not wrong, when running inference after creating a DetectionEngine should automatically delegate works to TPU. However, I'm wondering if all operation were mapped to the edgetpu during compilation. Any operation that was not mapped to the tpu will be executed on the CPU, can you provide the log file generated by the edgetpu_compiler by any chance (it should give very nice details on which operations are mapped to the edgetpu and which are not)?
from edgetpu.
No problems!
from edgetpu.
Related Issues (20)
- Coral Camera for Google Coral TPU is not available through any site
- Yolox-nano tfl.strided_slice op not supported on DarwiNN
- Edgetpu Compiler Compile Error HOT 1
- Issue while converting ONNX to TFlite.
- Edgetpu Compiler Compile Error
- Help understanding edgetpu compiler optimizations
- Inference Slower than claimed and using too much CPU.
- ASPM support?
- Wifi options not available in network manager after using the nmtui command on the coral devboard
- Coral dev board IOMMU support
- IMX8PLUS need enable MSI-X for M2 TPU accelerator
- test_data folder models documentations ?
- CORAL TPU M.2 B+M MODULE ([212-G650-04686-01]) M2 SATA not detected in HAOS HOT 2
- Not working on MacOS 14. (Python 3.9.6)
- TensorFlow Lite Object Detection Models on the Raspberry Pi (with Optional Coral USB Accelerator) Segmentation Fault HOT 1
- Why isn't this being updated?
- Possible overheating while reported temperature is normal HOT 2
- U-boot command saveenv is not working for Google Coral Mini. Cannot set bootdelay 0
- ERROR: Didn't find op for builtin opcode 'TRANSPOSE_CONV' version '4'. An older version of this builtin might be supported.
- Error in device opening /dev/apex_0 on kernel 6.6.28 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 edgetpu.