Keep only the Vulkan FP16 variant

README.md

@@ -26,7 +26,6 @@ revision `ac7e1c817ecab7c7dff5ce6b1abba61cd213ff29`.
 | `xnnpack/u2netp_xnnpack_fp32.pte` | xnnpack | fp32      |
 | `xnnpack/u2netp_xnnpack_int8.pte` | xnnpack | selective int8 / fp32 |
 | `vulkan/u2netp_vulkan_fp16.pte` | vulkan | fp16 with one fp32 convolution |
-| `vulkan/u2netp_vulkan_fp32.pte` | vulkan | fp32 |
 
 The exports take RGB float32 `[1,3,320,320]` input in `[0,1]` and return one
 float32 `[1,1,320,320]` foreground logit map. Image-maximum scaling and ImageNet
@@ -54,8 +53,7 @@ calibration, validation and rejected alternatives.
 
 Vulkan FP16 preserves input normalization and one sensitive convolution in FP32.
 On a Galaxy S20+ (Android 13, Mali), native forward medians were 337 ms for this
-variant and 403 ms for Vulkan FP32, versus 316 ms for XNNPACK FP32 and 189 ms
-for selective INT8. Vulkan is optional; Android retains its XNNPACK FP32
+variant, versus 316 ms for XNNPACK FP32 and 189 ms for selective INT8. Vulkan is optional; Android retains its XNNPACK FP32
 default. Across 13 device-tested images, Vulkan FP16 averaged 0.9945 mask IoU
 against FP32 (minimum 0.9854). See [Vulkan precision notes](vulkan/NOTES.md)
 for the export recipe, phone validation and timing limitations.
@@ -67,10 +65,9 @@ config.json                                    28 B
 coreml/config.json                           1.5 kB
 coreml/u2netp_coreml_fp16.pte                3.3 MB
 coreml/u2netp_coreml_fp32.pte                5.5 MB
-vulkan/config.json                           1.5 kB
-vulkan/NOTES.md                              4.2 kB
+vulkan/config.json                            886 B
+vulkan/NOTES.md                              4.1 kB
 vulkan/u2netp_vulkan_fp16.pte                2.4 MB
-vulkan/u2netp_vulkan_fp32.pte                4.6 MB
 xnnpack/config.json                          1.5 kB
 xnnpack/NOTES.md                             6.6 kB
 xnnpack/u2netp_xnnpack_fp32.pte              4.6 MB

vulkan/NOTES.md

@@ -1,7 +1,7 @@
 # Vulkan precision and Android validation
 
-Both variants accept RGB float32 `[1,3,320,320]` in `[0,1]` and return float32
-`[1,1,320,320]` foreground logits. Input normalization stays in FP32. Each
+The published FP16 variant accepts RGB float32 `[1,3,320,320]` in `[0,1]` and returns float32
+`[1,1,320,320]` foreground logits. Input normalization stays in FP32. The
 export contains one Vulkan delegate for the network and one portable input
 `amax` reduction. Texture limits are capped at 2048 in each dimension.
 
@@ -33,10 +33,9 @@ XNNPACK FP32 `.pte`, not ground-truth segmentation accuracy.
 | Variant | Mean mask IoU (13 images) | Minimum mask IoU | File size |
 | --- | --- | --- | --- |
 | Vulkan FP16 with one FP32 convolution | 0.9945 | 0.9854 | 2,437,516 B |
-| Vulkan FP32 | 0.999999 | 0.999986 | 4,646,540 B |
 
-The FP16 probability MAE was at most 0.00444 across those 13 images. Both
-variants produced finite outputs on all 15 inputs.
+The FP16 probability MAE was at most 0.00444 across those 13 images. The published
+variant produced finite outputs on all 15 inputs.
 
 Warm native forward measurements on the same bicycle input used three warm-up
 runs followed by ten measured runs per variant:
@@ -46,7 +45,7 @@ runs followed by ten measured runs per variant:
 | XNNPACK FP32 | 315.6 ms |
 | XNNPACK selective INT8 | 189.1 ms |
 | Vulkan FP16 with one FP32 convolution | 337.2 ms |
-| Vulkan FP32 | 403.1 ms |
+| Vulkan FP32 (unpublished trial) | 403.1 ms |
 
 These were sequential host-driven device checks, not interleaved benchmarks;
 they exclude model loading, image preprocessing and rendering. Vulkan does not
@@ -86,6 +85,6 @@ runpy.run_module("exporter.cli", run_name="__main__")
 PY
 ```
 
-The release exports were byte-identical to the device-validated candidates.
+The release FP16 export was byte-identical to the device-validated candidate.
 The Python wheel's native runtime cannot execute Vulkan on this Mac; it was
 not used as a substitute for phone validation.

vulkan/config.json

@@ -38,37 +38,6 @@
         }
       },
       "size_bytes": 2437516
-    },
-    {
-      "file": "u2netp_vulkan_fp32.pte",
-      "precision": "fp32",
-      "methods": {
-        "forward": {
-          "inputs": [
-            {
-              "shape": [
-                1,
-                3,
-                320,
-                320
-              ],
-              "dtype": "float32"
-            }
-          ],
-          "outputs": [
-            {
-              "shape": [
-                1,
-                1,
-                320,
-                320
-              ],
-              "dtype": "float32"
-            }
-          ]
-        }
-      },
-      "size_bytes": 4646540
     }
   ]
 }

vulkan/u2netp_vulkan_fp32.pte

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:88523d0b54ec20e9129194f110955cbc6d2f5d90b2293c9a712636fb5d255212
-size 4646540