Closed innat closed 7 months ago
Hi @innat , use .eval()
on the model. Also preferably use the weights=
API:
from torchvision.models.video import Swin3D_T_Weights
torch_model = torchvision.models.video.swin3d_t(
weights=Swin3D_T_Weights.KINETICS400_V1
).eval()
🐛 Describe the bug
I tired to do some simple inference using
torchvision.models.video.swin3d_t
model with input ofnp.ones
but each time I run the inference the output gets changed.Versions
torchvision.version == 0.16.0+cu121