Closed ConnorBaker closed 1 year ago
Hi, the standard validation dataset for Synthetic training can be downloaded at here.
You can also manually split a validation dataset from the training data in training. But in this way you must evaluate the trained model again on the standard validation dataset.
Thank you!
May I email you with some questions about training on larger images / using the synthetic burst pipelines? I understand if would rather not!
Thank you again for sharing your work :)
Thank you!
May I email you with some questions about training on larger images / using the synthetic burst pipelines? I understand if would rather not!
Thank you again for sharing your work :)
No problem. You can email me if you have any questions.
Hello,
Thank you for sharing your code!
I have a fork (https://github.com/ConnorBaker/BSRT) where I updated CUDA/PyTorch and switched to the DCN implementation offered by
torchvision
(details here: https://pytorch.org/vision/stable/generated/torchvision.ops.deform_conv2d.html#torchvision.ops.deform_conv2d). However,torchvision
's DCN expects the second dimension ofweights
to be divided by the number of groups, which causes an error when trying to use the pre-trained model, since the sizes of the tensors don't match. I tried to work around this so I could still use your pre-trained model, but was unable to: see https://github.com/ConnorBaker/BSRT/commit/7d9c5bdb873693109fab2a8217e482f0cf5c6ee9 for details and https://github.com/ConnorBaker/BSRT/commit/8b8339491205bdbddf14ffdea01cc92584e24939 for the full switch over.How can I train this model? I tried to get access to the full Zurich RAW to RGB (ZRR) dataset, but it is no longer available. Without the validation data (
val
directory from ZRR), I get errors when I try to run training (see example below).Any ideas?
Many thanks, Connor
Example run with training: