Csaba Botos

# Differential test of Domain Adaptation module: For reference, to make sure that these modifications didn't ruin the underlying model's performance (i.e. **without the domain adaptation** turned on durinng training...

> There might be something wrong with your sim10k or cityscapes car annotation I downloaded the dataset from the original sources and used the provided conversion scripts. The correctness of...

> Just in case you didn't realize it, the Cityscapes conversion scripts in this repo would generate a json file with 9 classes(including background) and class car would be mapped...

I've investigated the counts of instances in the converted COCO format json. The two scripts are functioning differently. `tools/cityscapes/convert_cityscapes_to_coco.py` -> category_id for cars = 3 | BBOX mode = (x,...

So after adding +1 to the W and H parameters of the boxes, the results are the same: `OrderedDict([('bbox', OrderedDict([('AP', 0.21999040175783008), ('AP50', 0.40802113381174443), ('AP75', 0.21781745864063617), ('APs', 0.02603636904496653), ('APm', 0.2231147873458656), ('APl',...

> Could you tell me how do you get the conversion code in your commit? `cp ../Detectron-DA-Faster-RCNN/tools/convert_cityscapes_to_caronly_coco.py tools/`. I ran the script this way: `python ../Detectron-DA-Faster-RCNN/tools/convert_cityscapes_to_caronly_coco.py --dataset cityscapes_car_only --outdir Detectron-DA-Faster-RCNN-cityscapes/...

> Adversarial training is very unstable. It's quite normal that the performance of your final checkpoints in different trials vary a lot and the best performance is obtained before the...

thanks, that's really helpful to know. Could you please also explain why do you do permutations here? https://github.com/krumo/Domain-Adaptive-Faster-RCNN-PyTorch/blob/fe0d30583ec0d1c1854861e930a91994f6e08dc2/maskrcnn_benchmark/modeling/da_heads/loss.py#L70-L75

also here I think the concatenation has to be carried out on dim=1 (after flattening) https://github.com/krumo/Domain-Adaptive-Faster-RCNN-PyTorch/blob/fe0d30583ec0d1c1854861e930a91994f6e08dc2/maskrcnn_benchmark/modeling/da_heads/loss.py#L80-L81 Because otherwise you would have different length vectors for different sizes after flattening (one...

Hi, Thanks for the amazing job! Any update on this?