Regression tests of all methods on VGG19
adrhill opened this issue · comments
Adrian Hill commented
Metalhead disabled pretrained weights in 0.6.0
due to model inaccuracies.
These can technically still be loaded while they are being fixed:
model = VGG19()
Flux.loadparams!(model.layers, weights("vgg19"))
However, the VGG19 weights are a 548 MB download every time CI is run. It might therefore be more reasonable to use a smaller model. Currently, MetalheadWeights contains (in ascending size):
- SqueezeNet (5 MB) -> requires
Parallel
for "fire" modules - GoogLeNet (27 MB) -> requires
Parallel
- Densenet121 (31 MB) -> requires
SkipConnection
- ResNet-50 (98 MB) -> requires
Parallel
,skip_identity
- VGG-19 (548 MB)
An easy workaround would be to run the methods on randomly initialized parameters (with fixed seed). The explanations w.r.t. to this model should still stay constant.