Image classification mix task: mix help classify_image

Command line arguments:

• -m, --model: Required. File path of .tflite file.
• -i, --input: Required. Image to be classified.
• -l, --labels: File path of labels file.
• -k, --top: Default to 1. Max number of classification results.
• -t, --threshold: Default to 0.0. Classification score threshold.
• -c, --count: Default to 1. Number of times to run inference.
• -a, --mean: Default to 128.0. Mean value for input normalization.
• -s, --std: Default to 128.0. STD value for input normalization.
• -j, --jobs: Number of threads for the interpreter (only valid for CPU).
• --use-tpu: Default to false. Add this option to use Coral device.
• --tpu: Default to "". Coral device name.
  • "" -- any TPU device
  • "usb" -- any TPU device on USB bus
  • "pci" -- any TPU device on PCIe bus
  • ":N" -- N-th TPU device, e.g. ":0"
  • "usb:N" -- N-th TPU device on USB bus, e.g. "usb:0"
  • "pci:N" -- N-th TPU device on PCIe bus, e.g. "pci:0"

Code based on classify_image.py