tucan9389 / tf2-mobile-2d-single-pose-estimation

:dancer: Pose estimation for iOS and android using TensorFlow 2.0
Apache License 2.0
167 stars 41 forks source link

Experiments #39

Open tucan9389 opened 4 years ago

tucan9389 commented 4 years ago

Table

tucan9389 commented 4 years ago

Experiment02

Dataset Config

Training Config

Result

Summary

Following PCKh@.5s are evaluated with AI Challenger's validation set.

Name Backbone PCKh@.5 tflite size input shape output shape
CPM MobileNetV2 92.91% 4.1MB [1,192,192,3] [1,24,24,14]
Hourglass MobileNetV2 72.58% 1.9MB [1,192,192,3] [1,48,48,14]
SimplePose ResNet18 97.22% 61.5MB [1,192,192,3] [1,48,48,14]

Tensorboard

Preparing...

tucan9389 commented 4 years ago

Experiment03

models from https://github.com/edvardHua/PoseEstimationForMobile/tree/master/release

Result

Summary

Following PCKh@.5s are evaluated with AI Challenger's validation set.

Name Backbone PCKh@.5 tflite size input shape output shape
CPM MobileNetV2 96.29% 2.4MB [1,192,192,3] [1,96.96,14]
Hourglass MobileNetV2 94.93% 1.7MB [1,192,192,3] [1,48,48,14]
aitikgupta commented 4 years ago

The values of PCKh@0.5 and tflite size seem to be empty for Experiment03. Are you planning to update it?

tucan9389 commented 4 years ago

@aitikgupta

The values of PCKh@0.5 and tflite size seem to be empty for Experiment03. Are you planning to update it?

Sure. I update it just now.

aitikgupta commented 4 years ago

For Experiment02, where could I find the configuration and tflite files?

tucan9389 commented 4 years ago

For Experiment02, where could I find the configuration and tflite files?

Here are the tflite files. cfg files are placed on config/training folder.

https://github.com/tucan9389/tf2-mobile-pose-estimation/releases/tag/experiment02

aitikgupta commented 4 years ago

Thanks, could you also release the corresponding frozen .pb files too? I wanted to compare them with my trained model.

tucan9389 commented 4 years ago

Thanks, could you also release the corresponding frozen .pb files too? I wanted to compare them with my trained model.

I just have saved_model now. If you open new issue for this, I’ll share soon. Thank you.

tucan9389 commented 4 years ago

Experiment04

Hyperparameters

Results

Stage num PCKh@.5 tflite size
1 60.16% 2.8MB
2 60.24% 3.3MB
3 62.38% 3.7MB
4 93.27% 4.2MB
5 92.82% 4.7MB

Experiment05

# Channels PCKh@.5 tflite size
1 [256, 256] 77.58% 9.3MB

Comments

The first PCKh@.5 doesn't satisfy. I'll reconstruct and experiment again.