fix a model inference problem on cpu

[spacewalk01]

1. I run keypoint.ipynb on a cpu-machine (macbook). And I got the following problem:

----> 2 weigths = torch.load('yolov7-w6-pose.pt')
...
RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are running on a CPU-only machine, please use torch.load with map_location=torch.device('cpu') to map your storages to the CPU.

2. So, as it suggests, I have added map_location=torch.device(device) option to load function but it turns out one of the convolutions used in the model was not designed for 'half' precision when running on cpu and I got the following error.

RuntimeError: "slow_conv2d_cpu" not implemented for 'Half'

3. Then, I removed half precision option from the notebook and added _ = model.float().eval() to run it on both cpu and gpu machines.
   I suppose a lot of folks like me will try it on cpu for demo test.

I have tested the fixed code on both cpu and gpu in google colab and the link is here:
https://colab.research.google.com/drive/1kqdVq-n8I0EcPRA2g7YYK70rArUmy6Ai?usp=sharing

[spacewalk01]

https://colab.research.google.com/drive/1kqdVq-n8I0EcPRA2g7YYK70rArUmy6Ai?usp=sharing
accessible to anyone with link

[spacewalk01]

@AlexeyAB

[spacewalk01]

Edited as you suggested and tested it on colab. Thank you for the review.