This project is Pose Estimation on iOS with ML Kit.
If you are interested in iOS + Machine Learning, visit here you can see various DEMOs.
Jointed Keypoints | Concatenated heatmap |
---|---|
(preparing...) |
Video source: https://www.youtube.com/watch?v=EM16LBKBEgI
Pose Estimation model for TensorFlow Lite(model.tflite
)
☞ Download TensorFlow Lite model model_cpm.tflite or hourglass.tflite.
input_name_shape_dict = {"image:0":[1,224,224,3]} image_input_names=["image:0"]
output_feature_names = ['Convolutional_Pose_Machine/stage_5_out:0']
cpm | hourglass | |
---|---|---|
Input shape | [1, 192, 192, 3] |
[1, 192, 192, 3] |
Output shape | [1, 96, 96, 14] |
[1, 48, 48, 14] |
Input node name | image |
image |
Output node name | Convolutional_Pose_Machine/stage_5_out |
hourglass_out_3 |
cpm | hourglass | |
---|---|---|
iPhone XS | (TODO ) |
(TODO ) |
iPhone XS Max | (TODO ) |
(TODO ) |
iPhone XR | (TODO ) |
(TODO ) |
iPhone X | 57 ms | 33 ms |
iPhone 8+ | (TODO ) |
(TODO ) |
iPhone 8 | (TODO ) |
(TODO ) |
iPhone 7 | (TODO ) |
(TODO ) |
iPhone 6 | (TODO ) |
(TODO ) |
Or you can use your own PoseEstimation model
-
(Preparing...)