Add regnet model from SWAG

[YosuaMichael]

subtask of #5708

Adding weight of regnet_y_16gf and regnet_y_32gf model from https://github.com/facebookresearch/SWAG

[facebook-github-bot]

💊 CI failures summary and remediations

As of commit 9904358 (more details on the Dr. CI page):

---

✅ None of the CI failures appear to be your fault 💚

---

• 2/2 broken upstream at merge base 96f2c0d since Apr 01

---

🚧 2 ongoing upstream failures:

These were probably caused by upstream breakages that are not fixed yet.

• unittest_windows_cpu_py3.8 since Apr 01 (3925946)
  • 🔁 rerun
• unittest_windows_cpu_py3.9 since Apr 01 (3925946)
  • 🔁 rerun

---

This comment was automatically generated by Dr. CI (expand for details).

Please report bugs/suggestions to the (internal) Dr. CI Users group.

Click here to manually regenerate this comment.

[YosuaMichael]

I run the test on imagenet1k val data with the following command:

# RegNet_Y_16GF_Weights.IMAGENET1K_SWAG_V1:
python -u ~/script/run_with_submitit.py --timeout 3000 --ngpus 1 --nodes 1 --partition train --model regnet_y_16gf --data-path="/datasets01_ontap/imagenet_full_size/061417" --test-only --batch-size=1 --weights="RegNet_Y_16GF_Weights.IMAGENET1K_SWAG_V1"
# Acc@1 86.012 Acc@5 98.054

#RegNet_Y_32GF_Weights.IMAGENET1K_SWAG_V1
python -u ~/script/run_with_submitit.py --timeout 3000 --ngpus 1 --nodes 1 --partition train --model regnet_y_32gf --data-path="/datasets01_ontap/imagenet_full_size/061417" --test-only --batch-size=1 --weights="RegNet_Y_32GF_Weights.IMAGENET1K_SWAG_V1"
# Acc@1 86.838 Acc@5 98.362

[datumbox]

LGTM, thanks!