Closed juliiami closed 1 year ago
@annxingyuan Do you know why inference result can be different on different device/os versions?
Hi @juliiami - would you mind visiting https://js.tensorflow.org/debug/ on both platforms and pasting your results in this ticket? Thanks!
Hi @juliiami - would you mind visiting https://js.tensorflow.org/debug/ on both platforms and pasting your results in this ticket? Thanks!
Hi @annxingyuan. The results look the same On the 1st device: On the 2nd:
I am having the same issue also where I observe different results across different devices with the same OS and browser for a completely different model. I am also able to replicate what @juliiami mentioned with his mobile net:
System 1 with i7-4720HQ and GTX965M on Chrome 89.0.4389.82:
System 2 with i7-9750H and RTX2070 MaxQ on Chrome 89.0.4389.82:
I have already read online that it might be due to how the browser handles the image processing but that could be wrong. Also on my model, the results are inconsistent enough that the top prediction is different for the two systems. Any pointers would be appreciated.
I also observed the same issue after visiting https://juliiami.github.io/tfjs_example/index.html. The results shown here https://js.tensorflow.org/debug/ are the same on all browsers though.
Browser | Device | OS | Probability of Egyptian cat |
---|---|---|---|
Chrome - Version 89.0.4389.90 (Official Build) (x86_64) | Macbook Pro | Mac OS 11.2.2 | 0.589 |
Safari - Version 14.0.3 (16610.4.3.1.4) | Macbook Pro | Mac OS 11.2.2 | 0.687 |
Safari | iPhone X | iOS 14.4.2 | 0.680 |
Chrome - v90.0.4430.216 | iPhone X | iOS 14.4.2 | 0.680 |
Chrome - v81.0.4044.138 | Galaxy s9+ | Android 10; SM-G965U Build/QP1A. 190711.020 | 0.65 |
I actually came to this thread because I am observing a similar issue for an audio classification model I run in the browser with the latest version of tfjs. I am observing significantly different predictions for audio in certain browsers/devices. I think (but am still investigating) that the issue is due to tfjs because I saved the data right before it went into tfjs on those devices the model is performing poorly, and I then ran it through my python version of the tensorflow model and it performs as expected.
Hi @juliiami, Apology for the late response. May I know if your issue has been resolved or still you are looking for the solution ? Thank You!
This issue has been automatically marked as stale because it has not had recent activity. It will be closed in 7 days if no further activity occurs. Thank you.
Closing as stale. Please @mention us if this needs more attention.
System information
I slightly modified the script provided in https://github.com/tensorflow/tfjs-examples/tree/master/mobilenet, my current version is here: https://github.com/juliiami/juliiami.github.io/tree/master/tfjs_example (corresponding webpage is here: https://juliiami.github.io/tfjs_example/index.html).
OS Platform and Distribution: checked on 2 laptops
Current behavior
Model predictions are different on 2 devices: 1.
2.
Checked also with tf.ENV.set("WEBGL_PACK", false), it doesn't influence on the predictions.