Actually, my question is very simple. I would like to use my own data in tensorflow lite model. So, i wrote these line of codes: Also, this is the error that I encountered: Answer This happens when the Dataloader cannot infer the labels of your images. The images should be divided into subfolders according to the class they belong to:
Tag: tensorflow-lite
How to continue training with checkpoints using object_detector.EfficientDetLite4Spec tensorflow lite
Preciously I have set my EfficientDetLite4 model “grad_checkpoint=true” in config.yaml. And it had successfully generated some checkpoints. However, I can’t figure out how to use these checkpoints when I want to continue training based on them. Every time I train the model it just start from the beginning, not from my checkpoints. The following picture shows my colab file system
Convert yolov4-tiny to transflow lite: ValueError: cannot reshape array of size 374698 into shape (256,256,3,3)
As I try to covert my yolov4-tiny custom weight to tftile, it always happen. This is what I input: And the wrong message appear. I have checked my labels.txt and there is no space or more lines.Also, I have changed the name in config.py. Is there any way to solve this problem? Thanks for help! Attach part of my code,
Loading Python 2D ndarray into Android for inference on TFLite
I’d like to test inference on a TensorFlow Lite model I’ve loaded into an Android project. I have some inputs generated in a Python environment I’d like to save to a file, load into my Android app and use for TFLite inference. My inputs are somewhat large, one example is: <class ‘numpy.ndarray’>, dtype: float32, shape: (1, 596, 80) I need
tflite: get_tensor on non-output tensors gives random values
I’m trying to debug my tflite model, that uses custom ops. I’ve found the correspondence between op names (in *.pb) and op ids (in *.tflite), and I’m doing a layer-per-layer comparison (to make sure the outputs difference are always in range 1e-4 (since it blows up at the end, I want to find the exact place where my custom layer