CODEWITHSUNDEEP
tensorflow2.0resnetquantizationtensorflow-litedensenet
Stefano555
Stefano555

Reputation: 41

TensorFlow Lite Full-Integer Quantization fails in TF 2

I've trained resnet50v2 and densenet 169 models. TensorFlow nightly 2.3.0-dev20200608. The model works fine and I tried some optimization such as "simple" tf lite, tf lite dynamic range, tf lite 16float, and they all work fine (the accuracy is either identical to the original or slightly lower as expected). I want to convert my model to use full-integer post-training quantization with uint8. I converted my model from SavedModel format with:

converter = tf.lite.TFLiteConverter.from_saved_model('/path/to/my/saved_models')
converter.optimizations = [tf.lite.Optimize.DEFAULT]
def representative_dataset_gen():
    for i in range(100):
        yield [x_train[i].astype(np.float32)]
converter.representative_dataset = representative_data_gen
converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS_INT8]
converter.inference_input_type = tf.uint8
converter.inference_output_type = tf.uint8
tflite_model = converter.convert()

with open('resnet.tflite', 'wb') as f:
  f.write(tflite_model)

as written in the TensorFlow lite website. I then compiled the model for edge tpu. It works, in the sense that edge tpu allows me to run it without errors but results are gibberish. It predicts always the same value. I tried then on cpu with tf lite interpreter. Input/output tensor are correctly uint8, but again it predicts again the same value. On cpu wiht tf lite issue persists moving to int8. Has anyone else experienced the same issue?

Please find here a Google folder with the code I use to convert, the model before and after conversion, and the converted model.

https://drive.google.com/drive/folders/11XruNeJzdIm9DTn7FnuIWYaSalqg2F0B?usp=sharing

Upvotes: 2

Views: 337

Answers (0)

Related Questions