Search results

Hi,I meet the problem in converting model to model_none.tflite in other challenge, Can you tell me how can you convert sucessfully? code： converter = tf.lite.TFLiteConverter.from_keras_model(model_tf.build(input_shape=(1,None,None,30))) converter.experimental_new_converter = True tflite_model...

Final Submission Instructions "model_none.tflite" should be: - a floating-point FP32 model (no FP16 / INT16 / INT8 quantization). - with an input tensor of size [1, None, None, 30] taking 10 RGB images as an input. - with an output tensor of size [1, None, None, 30] producing the 10 final...

hi, the use of extra data to train model possibly has any effect on the final psnr， does it affect the ranks？ Will the use of external data or not use external data will rank separately？

hello, Are you sure the train cannot use Val dataset？ Will you evaluate the submission on your private test data?

According to the codelab description，The model will be run using AI Benchmark (FP16 mode + TFLite GPU delegate). It does not require the model to be float32 or float16 or int8. Sometimes int8 quantization model is more faster than other. Must the model be float16 ?

Hi， Q1： Is the value of the input data limited to 0-1 or 0-255 , or does the user specify it in the users‘ readme? Q2： What is the data format of input frame？ input： [1,180,320,30] 1) rgb or bgr? 2) if the format is rgb, the channels first (rr....r gg..g bb..b...

Hi, I found the readme in Codalab haven’t fixed， Will it change back to the original format later？

Thank you for reply。 what does Energy consumption per inference mean？ Can you explain in more detail ？ I get latency and GPU memory from the app "AI-benchmark", But there isnot the item of energy. How can we get this value？

Please give some information. Three days have passed.

hello， When will the evaluation method be released ?

Hello, I'm trying to submit the results,but it failed. Error: Traceback (most recent call last): File "/tmp/codalab/tmp2Ey5ZM/run/program/evaluate.py", line 69, in print("Energy: {}".format(energy)) NameError: name 'energy' is not defined There arenot dirs in ZIP archive ,only files。 The...