How to create model with custom input_size #313
Replies: 1 comment
-
@kondounagi you don't create the model with an input_size, the models are fully convolutional and img size agnostic with the exception of vision_transformer which is fixed to a certain size. The default_cfg attached to the model is just metadata to indicate what resolution the datapipeline should be setup with to match the pretrained weights. In the example train.py script, the input size fed to the model is determined by the data loader setup here: https://github.com/rwightman/pytorch-image-models/blob/master/train.py#L477 Earlier on, the value of that input_size is resolved between the default_args in the model and the command line input args here: The arg |
Beta Was this translation helpful? Give feedback.
-
Hello. Thank you @rwightman for this great repository !
I'm wondering whether
timm.create_model()
can specify custominput_size
.For example, is it possible for
mobilenetv3_large_075
to set(3, 800, 800)
asinput_size
, which is different from original(3, 224, 224)
indefault_cfg
?I found no documentation about this custom
input_size
.If you could tell me how to do that, I'm please to write documentation as a contribution to this repository !
Beta Was this translation helpful? Give feedback.
All reactions