Hi! Thank you for a great paper and for sharing the code!
I'm looking to reproduce your results on the MoCo model, especially for transferring it to the CUB dataset.
The command I'm running is:
CUDA_VISIBLE_DEVICES=0 python transfer_linear_eval.py \
--pretrain-data imagenet100 \
--ckpt $CHECKPOINT_PATH \
--model resnet50 \
--dataset cub200 \
--datadir $CUB_DIR \
--metric top1
However, the model achieves accuracy lower than the one reported in the paper (37.0, as reported in Tab. 3):
For MoCo baseline (checkpoint shared by you) I got test acc=0.2575
and for MoCo_augself (checkpoint shared by you) I got test acc=0.3224
For MoCo pretrained by myself, I got test acc=0.3309
Thus, I think the issue may be in linear evaluation.
Oddly enough, I roughly reproduced your results on the CIFAR-10 and CIFAR-100 dataset (with ~0.5% difference), so maybe the issue is with CUB only.
Could you kindly provide some guidance on whether I got the hyperparameters right? Alternatively, how did you set up the CUB files - did you use the default train / test / split?
Best regards!
Hi! Thank you for a great paper and for sharing the code!
I'm looking to reproduce your results on the MoCo model, especially for transferring it to the CUB dataset.
The command I'm running is:
However, the model achieves accuracy lower than the one reported in the paper (37.0, as reported in Tab. 3):
For MoCo baseline (checkpoint shared by you) I got
test acc=0.2575and for MoCo_augself (checkpoint shared by you) I got
test acc=0.3224For MoCo pretrained by myself, I got
test acc=0.3309Thus, I think the issue may be in linear evaluation.
Oddly enough, I roughly reproduced your results on the CIFAR-10 and CIFAR-100 dataset (with ~0.5% difference), so maybe the issue is with CUB only.
Could you kindly provide some guidance on whether I got the hyperparameters right? Alternatively, how did you set up the CUB files - did you use the default train / test / split?
Best regards!