Search results

The submission instruction mail states the maximum number of entries have been increased to 10 but I still see it to be 3 -

Hi. Could someone clarify what is meant by test frames as mentioned in the last point of submission guidelines? > Download link(s) to the FULL results of ALL of the test frames Do test frames refer to the files we submit to the server that consist readme.txt, results.txt, and the TFLite model...

Yes, that should be the case. Cc: @tulasi1729

@Andrey Ignatov one final doubt regarding TFLite model for the challenge. If we fully integer quantize our models, then we should be good, right?

Thank you. Appreciate your help.

@Andrey Ignatov with this scaling, would this be affected as well (the final output of PyNet)? output_l0 = tf.nn.tanh(conv_l0_out) * 0.58 + 0.5

I see. Got your point. I had initially misunderstood it. On a related note, I have been able to run full-integer quantized models on DSPs (an example). So, do you think that might be a case here?

Got it. But didn't quite get "it is not supported by anyone" since TFLite Benchmark (v2) does support different quantizations including dynamic-range.

Also, if you could shed a bit more light on the core math to scale the pixel values when dealing with different bits of images (e.g. for 10 bits it's 4*255, for 14 bits it's 16*255) that would be very helpful.

Are you using Keras or TensorFlow for model conversion? - TensorFlow SavedModel What TensorFlow version did you use to convert the model? - TensorFlow 1.15.0 Is your model quantized or floating-point? - We used dynamic-range quantization. I am assuming we should not have used...

I see. So, the baseline script could have been updated accordingly here. @Andrey Ignatov

I serialized the output with integer data-type and kept the range to [0, 255]. Regarding your first question, this SO thread has some good explanations: https://stackoverflow.com/questions/58688633/how-to-convert-bayerrg8-format-image-to-rgb-image.

I tried to benchmark our TFLite model (generated using a TF 1.15 runtime) using the AI Benchmark app. Here are additional details: * Device model id: RMX1801. * Android Version: 8.1. * When exactly this problem appears: After clicking "Run Model" under "Custom Model" tab.

I tried to benchmark our model using the AI Benchmark app. After installing it on my phone (Realme Pro 2) it didn't open. Any clues?

Alrighty. Thank you.

@Andrey Ignatov following your PyNet work I was wondering what would be the right level (5, 4,...,0) for exporting the frozen graph for the latter TFLite conversion.

Great. Thank you.

Hi folks. I created a Colab Notebook in order to help the community get started with the provided scripts more quickly. It's now a part of the official baseline repository as well. I would be grateful if the Colab Notebook could be mentioned in the official channels.

Thank you so much @Andrey Ignatov. This is really helpful. During reporting the latency we are to report it on `[1, 544, 960. 4]` tensors, right? And we are free to use either mobile CPU or GPU?

The RAW validation images we are provided with are of 256x256 resolution. So, my question is what should be the size of the output RGB images? The competition homepage mentions it should be the same as the input size of the RAW images. But then again, the TFLite model's input size is different...

Could anyone clarify as to which latency (CPU/GPU) is to be recorded in readme.txt? Do I run the TFLite model on my mobile phone or on MediaTek Dimensity 1000+ (APU)? If the latter, then what is the suggested method?

The RAW images provided to us are 256x256 which is different from what's expected in the final model. So, what should be done here? One immediate thing we could do is resize the RAW images. But I wanted to know from the organizers to get more systematic directions.