Add `--half` support for FP16 CoreML exports with (#7446)

* add fp16 for coreml using --half

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* fix

* Cleanup

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Update export.py

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>

export.py

         LOGGER.info(f'\n{prefix} export failure: {e}')
 
 
-def export_coreml(model, im, file, prefix=colorstr('CoreML:')):
+def export_coreml(model, im, file, int8, half, prefix=colorstr('CoreML:')):
     # YOLOv5 CoreML export
     try:
         check_requirements(('coremltools',))
 
         ts = torch.jit.trace(model, im, strict=False)  # TorchScript model
         ct_model = ct.convert(ts, inputs=[ct.ImageType('image', shape=im.shape, scale=1 / 255, bias=[0, 0, 0])])
+        bits, mode = (8, 'kmeans_lut') if int8 else (16, 'linear') if half else (32, None)
+        if bits < 32:
+            if platform.system() == 'Darwin':  # quantization only supported on macOS
+                with warnings.catch_warnings():
+                    warnings.filterwarnings("ignore", category=DeprecationWarning)  # suppress numpy==1.20 float warning
+                    ct_model = ct.models.neural_network.quantization_utils.quantize_weights(ct_model, bits, mode)
+            else:
+                print(f'{prefix} quantization only supported on macOS, skipping...')
         ct_model.save(f)
 
         LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
 
     # Load PyTorch model
     device = select_device(device)
-    assert not (device.type == 'cpu' and half), '--half only compatible with GPU export, i.e. use --device 0'
+    if half:
+        assert device.type != 'cpu' or coreml, '--half only compatible with GPU export, i.e. use --device 0'
     model = attempt_load(weights, map_location=device, inplace=True, fuse=True)  # load FP32 model
     nc, names = model.nc, model.names  # number of classes, class names
 
     im = torch.zeros(batch_size, 3, *imgsz).to(device)  # image size(1,3,320,192) BCHW iDetection
 
     # Update model
-    if half:
+    if half and not coreml:
         im, model = im.half(), model.half()  # to FP16
     model.train() if train else model.eval()  # training mode = no Detect() layer grid construction
     for k, m in model.named_modules():
     if xml:  # OpenVINO
         f[3] = export_openvino(model, im, file)
     if coreml:
-        _, f[4] = export_coreml(model, im, file)
+        _, f[4] = export_coreml(model, im, file, int8, half)
 
     # TensorFlow Exports
     if any((saved_model, pb, tflite, edgetpu, tfjs)):