Sureshda

Hi @ElonXXIII , As in SSD models, these are the predictions based on predefined anchors. We use [TfLiteTensorsToDetectionsCalculator](https://github.com/google/mediapipe/blob/a2a63e387680c090f76072864a107647e874d390/mediapipe/graphs/hand_tracking/subgraphs/hand_detection_gpu.pbtxt#L91) to decode the output tensors given the [SSD anchors](https://github.com/google/mediapipe/blob/a2a63e387680c090f76072864a107647e874d390/mediapipe/graphs/hand_tracking/subgraphs/hand_detection_gpu.pbtxt#L64).

Hi @ArtfulMinx , Could you please check this https://github.com/google/mediapipe/issues/3539#issuecomment-1193091309 comments and confirm still if you have any error.

Hi @ArtfulMinx , Pose landmarks model is intended to be used with an image of a single person for now. We can't guarantee the same quality if there will be...

Hi @serrabii , Please check [this](https://google.github.io/mediapipe/getting_started/hello_world_ios.html#hello-world-on-ios) documentation for your reference and can build ios externally.

Hi @serrabii , These rules have recently moved and made it public ,could you test and verify.

@orsveri ,are you using same data for both the models?

Hi @ndrewtl , Could you please provide steps to reproduce this issue.

Hi @fchen09 , Could you please share any reference video and also if any code changes to investigate further on this issue.

Hi @fchen09 , We have closed issue which is having answer for queries on Z co-ordinate , could you please check that closed [issue](https://github.com/google/mediapipe/issues/1611#issuecomment-974941821).

Hi @BitLoose , Could you please confirm in which platfrom you trying this solution?