Search results

Will you announce the score of every team or just individual:)

yeah, thank you very much, and there is anothor now...😅

can you test the latest tflite submission on codalab, because deadline is coming...

I have converted the NONE_tflite successfully, but when to test on app, it raise error, how to do next?

but, the result may be different from 10 of 100, because out model need neighbour frames' information, so the results should only be used as a reference, not completely consistent?

Does the final result will be check by our provided TFLite models?(For PSNR) Due to VSR model, only 10 frames can't reproduce our 100 frames result

hello, why i press the submit button in the codalab, it is no response?

The final result is ： 1. the PSNR results of our original model (such as pytroch code) on 3000 frames 2. the speed of the provided tflite model at 10 frames. And we must ensure that the output of tflite and pytorch Exactly the same when given 10 frames. Is my following understanding correct...

Dose the TFLite Gpu delegates support tf.nn.depth_to_space op directly? (not run in cpu)

And for the scores, The score indicates that the PSNR is 1dB higher, which is equivalent to half of the running time. Obviously, if the model size is reduced to approximately 0, the output PSNR will be equal to the input PSNR，the score would be very high ! so, will you change the rule for fair...

that's to say, the tflite need to deal with 100 frames inputs in the later? (result infered in 100 frames is different with that infered on 10 frames, because the VSR model)

So tflite model is only used to test the forward time (when a video has only 10 frames), not the final result? thank you for your reply

Q1： is the test set only 300 frames? Can the model use the remaining 2700 frames? (the reds test dataset has 3000 frames) Q2: "During the final test phase, the participants will be asked to submit all the restored frames by email ", Is that 300 or 3000？