Recent content by JetDZC

  1. J

    High Dynamic Range Challenge

    Is this challenge still open? Why there are only two participants?
  2. J

    Real-Time Image Super-Resolution Challenge

    Couldn't agree with you more!
  3. J

    Real-Time Image Super-Resolution Challenge

    Me too!
  4. J

    Real-Time Image Super-Resolution Challenge

    Yes, we exactly need to do de-quantization. How can we achieve this?
  5. J

    Real-Time Image Super-Resolution Challenge

    How can we deal with this post scaling using zero point & scale? Thanks a lot!
  6. J

    Real-Time Image Super-Resolution Challenge

    Hello, can I ask you a question? How much does psnr decrease if using fully quantized model? I use quantize-aware training but the performance still decreases up to 5dB. I am wondering whether there is something wrong...
  7. J

    Real-Time Image Super-Resolution Challenge

    The quantized model without the following two lines loses small psnr, but if I uncomment them, psnr decreases from 29dB to 20dB. I want to know whether it is normal? [1].converter.inference_input_type = tf.uint8 [2].converter.inference_output_type = tf.uint8
  8. J

    Real-Time Image Super-Resolution Challenge

    Hello, after I click "Run" bottom in AI Benchmark App, the interface returns back to "Device AI-Score". What's the problem? --Tensorflow-gpu version: [2.2.0] --Conversion: [tf.lite.TFLiteConverter.from_concrete_functions] --Quantization type: [uint8]
See more
Top