TorchDSP / torchsig

TorchSig is an open-source signal processing machine learning toolkit based on the PyTorch data handling pipeline.
MIT License
170 stars 38 forks source link

Wideband Dataset Example Not plotting #125

Closed gvanhoy closed 1 year ago

gvanhoy commented 1 year ago

Describe the bug The 03 example notebook is not working correctly on branch v0.3.0

To Reproduce Steps to reproduce the behavior:

from torchsig.datasets.wideband_sig53 import WidebandSig53
import torchsig.transforms.transforms as ST
from torchsig.transforms.target_transforms.target_transforms import DescToListTuple

target_transform = ST.Compose([
    DescToListTuple(),
])

ds = WidebandSig53(
    root='/wbsig53',
    train=False,
    impaired=True,
    transform=None,
    target_transform=target_transform,
    regenerate=False,
    use_signal_data=True,
    gen_batch_size=1,
    use_gpu=True,
)

for i in range(len(ds)):
    data, annotation = ds[i]
    for label_obj_idx in range(len(annotation)):
        print(annotation[label_obj_idx][0]

Expected behavior Plots should show.