Fix maskrcnn_resnet50_fpn_v2 weights _ops metadata

[YeonwooSung]

test_schema_meta_validation[maskrcnn_resnet50_fpn_v2] was skipped because stored _ops did not match get_ops().

_ops

• Old: 333.577
• New: 333.577 (unchanged)

How computed

• model = maskrcnn_resnet50_fpn_v2(weights=None) (same architecture as the published weights)
• get_ops(model, MaskRCNN_ResNet50_FPN_V2_Weights.COCO_V1, height=800, width=800) from test/common_extended_utils.py
• Input size 800x800 as in detection_models_input_dims
• model.eval(); result is round(flops, 3)
• Five seeds (0–4) all returned 333.577

Also verified num_params == sum(p.numel() for p in model.parameters()) (46359409).

Removed the pytest.skip for this model so the schema meta check runs again.

Fixes #7349

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/vision/9647

• 📄 Preview Python docs built from this PR

Note: Links to docs will display an error until the docs builds have been completed.

This comment was automatically generated by Dr. CI and updates every 15 minutes.