I have quantized ONNX model (exported from PyTorch). Is there any way to convert it to quantized TFLite model? It's important to apply quantization on the PyTorch side.
Related
I have a darknet yolov4 model that is converted to tflite file and trained by COCO dataset for object detection.
I want to train that for my traffic sign dataset. (GTSDB)
How should I do that for my tflite file?
I don't want to do that in darknet and then convert to tflite. I want to transfer learning directly from tflite file.
I have a trained Tensorflow model and a Tensorflow Lite model converted from it. If I provide them with the same input, should they give me the exact same output?
I'm trying to compile a tflite model with the edgetpu compiler to make it compatible with Google's Coral USB key, but when I run edgetpu_compiler the_model.tflite I get a Model not quantized error.
I then wanted to quantize the tflite model to an 8-bit integer format, but I don't have the model's original .h5 file.
Is it possible to quantize a tflite-converted model to an 8-bit format?
#garys unfortunately, tensorflow doesn't have an API to quantize a float tflite model. For post training quantization, the only API they have is for full tensorflow models (.pb, hdf5, h5, saved_model...) -> tflite. The quantization process happens during tflite conversion, so to my knowledge, there isn't a way to do this
General question: is there tooling to convert from tflite format to any other format?
I'm trying to convert a keras model to a CoreML model, but I can't because the model uses a layer type unsupported by CoreML (Gaussian Noise). Converting the keras .h5 model to a .tflite is simple, removes the offending layer (which is only used in training anyway), and performs some other optimisations. But it doesn't seem possible to convert out of the resultant tflite to any other format. Coremltools doesn't support tflite. I thought I could probably load the model from tflite into a tensorflow session, save a .pb from there, and convert that to coreml using coremltools, but I can't see a way to load the tflite model into a tensorflow session. I saw the documentation linked to in this question, but that seems to use the tflite interpreter to read the tflite model, rather than a "true" Tensorflow session.
Can someone point me to the Resnet34 pre-trained model on image-net using tensorflow? I am not sure but TF-slim trained model are same or would there be difference?
You can use Keras ResNet(18,34,50,101,152) pre-trained models https://github.com/qubvel/classification_models