Comments (7)
I went through everything I could think of to try to fix this, but nothing has worked so far.
Here are the things I've tried
1.) I trained my data using AlexNet with pretrained weights from the original alexnet bvlc_alexnet.caffemodel. This made the training extremely fast, and a hair under 100% for the accuracy that Digits reported. All the test images reported correct under digits with >89% confidence. But, one of the test images still failed on the TX1 imagenet-console. On further testing I realized that it was having issues with the playingcards that were slanted about 45 degrees. None of the 0 degree or 90 degree cards failed.
2.) from the jetson-inference source code it looked like the images were being resized to 227x227 so I tried resizing them to 227x227 to see what Digits reported with those sizes. Digits still reported them correctly.
3.) I tried changing the mean value subtraction to all 0.0f's, but that didn't seem to help at all. I didn't expect it to because the data is trained using mean subtraction.
4.) I tried disabling FP16, and then deleting the tensor caffe file before retrying. But, that didn't help. I didn't expect it to as everything I've read suggest that FP16 has no noticeable degradation in accuracy.
The only thing I can think of doing next is changing the mean value subtraction, but I don't know how to get those values yet. I'm a bit skeptical of that though, and it seems like a resizing issue.
Any suggestions on what to try?
from jetson-inference.
from jetson-inference.
The images I tested were 256x256. I purposely squashed them to this size to make sure they matched the size that Digits trained on.
I went ahead and uploaded the Model being used along with the Test Images.
https://github.com/S4WRXTTCS/PlayingCards
The Test Image it has problems on is Squashed4.jpg
from jetson-inference.
After investigating it further it seems it was related to the mean values.
I realized that use_archive.py was also giving me the same incorrect answer for that one example. Where it was completely off the results from digits.
One limitation of use_archive.py is it subtracts a mean pixel rather than the whole mean file. So that meant the mean subtraction was likely the culprit.
So I retrained the images using Mean Pixel subtraction instead of image in an attempt to at least get use_archive.py to report the same result as Digits.
The new Model worked for Digits+use_archive.py, and also gave me similar results with the jetson inference code.
from jetson-inference.
from jetson-inference.
Thanks for your help.
from jetson-inference.
@S4WRXTTCS hi ,i also train a GoogleNet image classification network on a custom dataset using the default Googlenet network within Digits. but i don't know how to move it to jetson-inference and use the model that i got it by training. could you tell me the detail. thank you very much. you can send email to me [email protected]
from jetson-inference.
Related Issues (20)
- Web-RTC dash not have argument on app.py
- [TRT] 2: [utils.cpp::checkMemLimit::380] Error Code 2: Internal Error (Assertion upperBound != 0 failed. Unknown embedded device
- SyntaxError: future feature annotations is not defined HOT 2
- where is file named train_ssd.py ? HOT 2
- cudaEventElapsedTime device not ready (error 600) (hex 0x258) HOT 1
- [ WARN:0] global /opt/opencv/modules/videoio/src/cap_gstreamer.cpp (935)
- How to open csi camera in a docker container HOT 3
- How to use custom .onnx or .tflite model with inference ? HOT 1
- Problem with testing video viewer function HOT 7
- choose network precision as float32 HOT 1
- Questions about how to receive and use ROS1 image msg
- RuntimeError: CUDA error: too many resources requested for launch
- how to get networks/FlowNet-320x240/flownets.onnx HOT 2
- Action Recognition gets crashed after running for couple of seconds
- Fail to load vgg-16 for inferencing on Jetson Nano 4GB HOT 1
- detectnet with GMSL Camera
- Is there a way to manually EOS in python object? HOT 2
- How to save videos through videosource, instead of using output.render HOT 1
- MobileNetV3 constant dips in accuracy.
- unable to download ResNet18-Tagging-VOC/resnet18.onnx
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 jetson-inference.