Round1 and Round2

Mono Depth Perception
#1

@dipam, could you please provide further details about the current situation? It appears that there is some confusion regarding the status of rounds 1 and 2. Additionally, updating the dataset at this stage of the competition seems unusual.

To clarify, it seems that round 1 has been completed, but there was no mention of it in the initial description. It is unclear what this means for the competition as a whole.

Furthermore, updating the dataset at this point in the competition seems questionable, especially if the previous dataset was used for calculating the leaderboard score. It is uncertain whether a new dataset will be used for the leaderboard calculation, and if so, how this will affect the competition.

#2

This was always the intention. The Amazon team was preparing the dataset for the past few months and only released it now for the final evaluations. Rest assured your solutions should work, the distribution of images in the new dataset is quite similar.

The validation data used for Round 1 was used for the leaderboard of Round 1. This has now been released publicly so anyone can use if for further training if he/she wishes.

I will check again if this was not communicated properly before, as I mentioned above this was always the intention.

#3

@dipam , thank you for clarification, now for me it looks understandable!