Martin Garbade
Martin Garbade
This is working! Thx a lot. I further added some lines to suppress the drawing of "NOT_LABELED" keypoints as can be seen from [this commit](https://github.com/mgarbade/coco-annotator/commit/100d0f43efdaced1e8eab646062e0499eb7418eb) (based on Matt Deboer's last...
This issue should not be stale in my opinion... Meanwhile I tried recompiling with some different versions of Mediapipe - tag 0.8.8 , commit: 33d683c67100ef3db37d9752fcf65d30bea440c4 - tag 0.8.9, commit: e6c19885c6d3c6f410c730952aeed2852790d306...
I wanted to understand tflite model inference, as I'm still struggling to make mediapipe use my own custom tflite model (for pose classification). Regarding my questions: Seems like I was...
Hmm I cannot open those links. It asks me to "sign in" (I'm not at google :stuck_out_tongue_winking_eye: )
As I'm still struggling with getting mediapipe inference running, let me expand on my problem: # [Mediapipe: Toy example using custom tflite graph](https://stackoverflow.com/questions/72448936/mediapipe-toy-example-using-custom-tflite-graph) I'm trying to dig into mediapipe and...
Some further findings (using the above code, but changing the graph definition) - this graph works: ``` input_stream: "in" output_stream: "out" node { calculator: "MatrixToTensorCalculator" input_stream: "in" output_stream: "tensor_features" }...
Ok, I finally found a "working" graph for my simple hello_world / tflite toy-example: ``` node { calculator: "TfLiteConverterCalculator" input_stream: "MATRIX:in" output_stream: "TENSORS:image_tensor" options: { [mediapipe.TfLiteConverterCalculatorOptions.ext] { zero_center: false }...
As far as I know, this connection is part of the original CMU publication as well. Reason might be that it helps the model training. More paf connections might help...
I assume the NHWC problem has been fixed by using tensorflow 2.x and the corresponding (most recent) version of onnx and onnx-tf. However in the most recent version other problems...
True, I was recently examining the tensorflow frozen graph (using tf 2.2 ) build from onnx and it still complains about the NHWC problem.