Fix config schema and explain Core ML precision

README.md

@@ -23,16 +23,27 @@ revision `91f3fd21e131641f51e8d35736d1958350180e3a`.
 | `base/vulkan/zipdepth_base_384_vulkan_fp16.pte` | vulkan | fp16 |
 | `base/xnnpack/zipdepth_base_384_xnnpack_fp32.pte` | xnnpack | fp32 |
 
+## Core ML precision
+
+The Core ML export uses FP32 because FP16 reduced numerical agreement with the
+float reference: across seven photos/illustrations, its worst range-normalized
+RMSE was 6.31% and minimum correlation was 0.970. FP32 reduced the worst
+range-normalized RMSE to below 0.00012%.
+
+Unlike the FP16 Core ML exports, this FP32 ML program runs on CPU/GPU and cannot
+use the Apple Neural Engine, even with compute units set to `ALL`; see
+[Apple's typed-execution guide](https://apple.github.io/coremltools/docs-guides/source/typed-execution.html).
+
 ## Repository structure
 
 ```
-config.json
-base/coreml/config.json
-base/coreml/zipdepth_base_384_coreml_fp32.pte       24.9 MB
-base/vulkan/config.json
-base/vulkan/zipdepth_base_384_vulkan_fp16.pte       12.8 MB
-base/xnnpack/config.json
-base/xnnpack/zipdepth_base_384_xnnpack_fp32.pte     24.6 MB
+config.json                                       30 B
+base/coreml/config.json                           847 B
+base/coreml/zipdepth_base_384_coreml_fp32.pte     24.9 MB
+base/vulkan/config.json                           847 B
+base/vulkan/zipdepth_base_384_vulkan_fp16.pte     12.8 MB
+base/xnnpack/config.json                          849 B
+base/xnnpack/zipdepth_base_384_xnnpack_fp32.pte   24.6 MB
 ```
 
 ## Compatibility

base/coreml/config.json

@@ -11,8 +11,6 @@
     {
       "file": "zipdepth_base_384_coreml_fp32.pte",
       "precision": "fp32",
-      "quantized": false,
-      "default": true,
       "methods": {
         "forward": {
           "inputs": [

base/vulkan/config.json

@@ -11,8 +11,6 @@
     {
       "file": "zipdepth_base_384_vulkan_fp16.pte",
       "precision": "fp16",
-      "quantized": false,
-      "default": true,
       "methods": {
         "forward": {
           "inputs": [

base/xnnpack/config.json

@@ -11,8 +11,6 @@
     {
       "file": "zipdepth_base_384_xnnpack_fp32.pte",
       "precision": "fp32",
-      "quantized": false,
-      "default": true,
       "methods": {
         "forward": {
           "inputs": [