Update Quantized Transfer Learning for Computer Vision tutorial to avoid use of copy.deepcopy()

[mikgor]

Fixes #2333

Description

Replace copy.deepcopy() with model.load_state_dict in Quantized Transfer Learning for Computer Vision tutorial.

[netlify]

✅ Deploy Preview for pytorch-tutorials-preview ready!

Name	Link
🔨 Latest commit	ae26b75
🔍 Latest deploy log	https://app.netlify.com/sites/pytorch-tutorials-preview/deploys/647e293a5ba2a400082ce69f
😎 Deploy Preview	https://deploy-preview-2417--pytorch-tutorials-preview.netlify.app
📱 Preview on mobile	Toggle QR Code... Use your smartphone camera to open QR code link.

---

To edit notification comments on pull requests, go to your Netlify site settings.

[NicolasHug]

Thank you for the PR @mikgor . I'm afraid the original code copy.deepcopy(model.state_dict()) is actually correct and doesn't need to be updated. I see #2333 was opened but I don't think it fits the original issue: here we're creating deepcopies of model.state_dict() which is a dict and that's a fine thing to do. The original problem stated in #2177 is about copying nn.Module but that's not the case here.

I don't think we should be merging this PR but let me see if we can still get you credits for it somehow

[svekars]

Thank you for looking into this @mikgor. We have recorded your contribution. Closing.