How was "We train using batches with 2 source images and 2 mixed images for 250k iterations" achieved in the code?

vikolss / DACS

Code from the paper "DACS: Domain Adaptation via Cross-domain Mixed Sampling"

MIT License

123 stars 19 forks source link

How was "We train using batches with 2 source images and 2 mixed images for 250k iterations" achieved in the code? #21

Open danielmao2019 opened 4 months ago

danielmao2019 commented 4 months ago

How was "We train using batches with 2 source images and 2 mixed images for 250k iterations" achieved in the code? I traced through the training code but did not see how this was implemented. Could anyone please point me to the class method/function that controls this part? Many thanks!