about Train/Val/Test Split

[amiltonwong]

trafficstars

Hi, @QingyongHu ,

According to Sec 4.1 in your paper, Train/Val/Test Split is briefly mentioned for Birmingham and Cambridge tiles. For better comparison with the baseline methods mentioned in your experiments, could you list the specific Train/Val split for Birmingham and Cambridge tiles in your experiment?

Thanks~

[yuan-zm]

Hi, @QingyongHu ,

I have the same question about Train/Val/Test Split of the datasets.

[yuan-zm]

Hi, @amiltonwong ,

I found the split here.

https://github.com/QingyongHu/SensatUrban/blob/a645399e836f980b05a46cc16f4f5cd773df81f2/main_SensatUrban.py#L27

self.val_file_name = ['birmingham_block_1',  'birmingham_block_5', 'cambridge_block_10',  'cambridge_block_7']       

self.test_file_name = ['birmingham_block_2', 'birmingham_block_8',  'cambridge_block_15', 'cambridge_block_22',                               'cambridge_block_16', 'cambridge_block_27']

However, according to Sec 4.1, there are 5 tiles in Cambridge for validation, here are only 2.

[codename1995]

Same questions. Any updates?

[Gaoyuan2]

Same questions. Any updates?