Update model card for yolov8-det

README.md

@@ -80,13 +80,11 @@ Full pipeline timing: pre-processing + inference + post-processing.
 
 ## Downloads
 
-### Universal Formats
+<details open>
+<summary><strong>ONNX FP32</strong> — Any platform with ONNX Runtime.</summary>
 
-<details>
-<summary><strong>ONNX FP32</strong> — Any platform with ONNX Runtime</summary>
-
-| Size | File | Download |
-|------|------|----------|
+| Size | File | Status |
+|------|------|--------|
 | Nano | `yolov8n-det-coco.onnx` | [Download](https://huggingface.co/EdgeFirst/yolov8-det/resolve/main/onnx/yolov8n-det-coco.onnx) |
 | Small | `yolov8s-det-coco.onnx` | [Download](https://huggingface.co/EdgeFirst/yolov8-det/resolve/main/onnx/yolov8s-det-coco.onnx) |
 | Medium | `yolov8m-det-coco.onnx` | [Download](https://huggingface.co/EdgeFirst/yolov8-det/resolve/main/onnx/yolov8m-det-coco.onnx) |
@@ -96,84 +94,31 @@ Full pipeline timing: pre-processing + inference + post-processing.
 </details>
 
 <details>
-<summary><strong>TFLite INT8</strong> — Any platform with TFLite (i.MX 8M Plus uses VX delegate)</summary>
-
-| Size | File | Download |
-|------|------|----------|
-| Nano | `yolov8n-det-coco-int8.tflite` | [Download](https://huggingface.co/EdgeFirst/yolov8-det/resolve/main/tflite/yolov8n-det-coco-int8.tflite) |
-| Small | `yolov8s-det-coco-int8.tflite` | [Download](https://huggingface.co/EdgeFirst/yolov8-det/resolve/main/tflite/yolov8s-det-coco-int8.tflite) |
-| Medium | `yolov8m-det-coco-int8.tflite` | [Download](https://huggingface.co/EdgeFirst/yolov8-det/resolve/main/tflite/yolov8m-det-coco-int8.tflite) |
-| Large | `yolov8l-det-coco-int8.tflite` | [Download](https://huggingface.co/EdgeFirst/yolov8-det/resolve/main/tflite/yolov8l-det-coco-int8.tflite) |
-| XLarge | `yolov8x-det-coco-int8.tflite` | [Download](https://huggingface.co/EdgeFirst/yolov8-det/resolve/main/tflite/yolov8x-det-coco-int8.tflite) |
-
-</details>
-
-### Platform-Specific
-
-<details>
-<summary><strong>NXP i.MX 93</strong> — Ethos-U NPU via ARM VELA compiler.</summary>
-
-| Size | File | Download |
-|------|------|----------|
-| Nano | `yolov8n-det-coco.tflite` | [Download](https://huggingface.co/EdgeFirst/yolov8-det/resolve/main/imx93/yolov8n-det-coco.tflite) |
-| Small | `yolov8s-det-coco.tflite` | [Download](https://huggingface.co/EdgeFirst/yolov8-det/resolve/main/imx93/yolov8s-det-coco.tflite) |
-| Medium | `yolov8m-det-coco.tflite` | [Download](https://huggingface.co/EdgeFirst/yolov8-det/resolve/main/imx93/yolov8m-det-coco.tflite) |
-| Large | `yolov8l-det-coco.tflite` | [Download](https://huggingface.co/EdgeFirst/yolov8-det/resolve/main/imx93/yolov8l-det-coco.tflite) |
-| XLarge | `yolov8x-det-coco.tflite` | [Download](https://huggingface.co/EdgeFirst/yolov8-det/resolve/main/imx93/yolov8x-det-coco.tflite) |
-
-</details>
-
-<details>
-<summary><strong>NXP i.MX 95</strong> — eIQ Neutron NPU optimized.</summary>
+<summary><strong>TFLite INT8</strong> — CPU or NPU via runtime delegate (i.MX 8M Plus VX Delegate).</summary>
 
-| Size | File | Download |
-|------|------|----------|
-| Nano | `yolov8n-det-coco.tflite` | [Download](https://huggingface.co/EdgeFirst/yolov8-det/resolve/main/imx95/yolov8n-det-coco.tflite) |
-| Small | `yolov8s-det-coco.tflite` | [Download](https://huggingface.co/EdgeFirst/yolov8-det/resolve/main/imx95/yolov8s-det-coco.tflite) |
-| Medium | `yolov8m-det-coco.tflite` | [Download](https://huggingface.co/EdgeFirst/yolov8-det/resolve/main/imx95/yolov8m-det-coco.tflite) |
-| Large | `yolov8l-det-coco.tflite` | [Download](https://huggingface.co/EdgeFirst/yolov8-det/resolve/main/imx95/yolov8l-det-coco.tflite) |
-| XLarge | `yolov8x-det-coco.tflite` | [Download](https://huggingface.co/EdgeFirst/yolov8-det/resolve/main/imx95/yolov8x-det-coco.tflite) |
+| Size | File | Status |
+|------|------|--------|
+| Nano | `yolov8n-det-coco.tflite` | [Download](https://huggingface.co/EdgeFirst/yolov8-det/resolve/main/tflite/yolov8n-det-coco.tflite) |
+| Small | `yolov8s-det-coco.tflite` | [Download](https://huggingface.co/EdgeFirst/yolov8-det/resolve/main/tflite/yolov8s-det-coco.tflite) |
+| Medium | `yolov8m-det-coco.tflite` | [Download](https://huggingface.co/EdgeFirst/yolov8-det/resolve/main/tflite/yolov8m-det-coco.tflite) |
+| Large | `yolov8l-det-coco.tflite` | [Download](https://huggingface.co/EdgeFirst/yolov8-det/resolve/main/tflite/yolov8l-det-coco.tflite) |
+| XLarge | `yolov8x-det-coco.tflite` | [Download](https://huggingface.co/EdgeFirst/yolov8-det/resolve/main/tflite/yolov8x-det-coco.tflite) |
 
 </details>
 
 <details>
-<summary><strong>NXP Ara240</strong> — Kinara DVM compiled model.</summary>
+<summary><strong>NXP i.MX 95 (eIQ Neutron)</strong> — eIQ Neutron NPU optimized.</summary>
 
-| Size | File | Download |
-|------|------|----------|
-| Nano | `yolov8n-det-coco.dvm` | [Download](https://huggingface.co/EdgeFirst/yolov8-det/resolve/main/ara240/yolov8n-det-coco.dvm) |
-| Small | `yolov8s-det-coco.dvm` | [Download](https://huggingface.co/EdgeFirst/yolov8-det/resolve/main/ara240/yolov8s-det-coco.dvm) |
-| Medium | `yolov8m-det-coco.dvm` | [Download](https://huggingface.co/EdgeFirst/yolov8-det/resolve/main/ara240/yolov8m-det-coco.dvm) |
-| Large | `yolov8l-det-coco.dvm` | [Download](https://huggingface.co/EdgeFirst/yolov8-det/resolve/main/ara240/yolov8l-det-coco.dvm) |
-| XLarge | `yolov8x-det-coco.dvm` | [Download](https://huggingface.co/EdgeFirst/yolov8-det/resolve/main/ara240/yolov8x-det-coco.dvm) |
+| Size | File | Status |
+|------|------|--------|
+| Nano | `yolov8n-det-coco.imx95.tflite` | [Download](https://huggingface.co/EdgeFirst/yolov8-det/resolve/main/imx95/yolov8n-det-coco.imx95.tflite) |
+| Small | `yolov8s-det-coco.imx95.tflite` | Coming Soon |
+| Medium | `yolov8m-det-coco.imx95.tflite` | Coming Soon |
+| Large | `yolov8l-det-coco.imx95.tflite` | Coming Soon |
+| XLarge | `yolov8x-det-coco.imx95.tflite` | Coming Soon |
 
 </details>
 
-<details>
-<summary><strong>RPi5 + Hailo-8/8L</strong> — Hailo-8L (13 TOPS) and Hailo-8 (26 TOPS).</summary>
-
-| Size | File | Download |
-|------|------|----------|
-| Nano | `yolov8n-det-coco.hef` | [Download](https://huggingface.co/EdgeFirst/yolov8-det/resolve/main/hailo/yolov8n-det-coco.hef) |
-| Small | `yolov8s-det-coco.hef` | [Download](https://huggingface.co/EdgeFirst/yolov8-det/resolve/main/hailo/yolov8s-det-coco.hef) |
-| Medium | `yolov8m-det-coco.hef` | [Download](https://huggingface.co/EdgeFirst/yolov8-det/resolve/main/hailo/yolov8m-det-coco.hef) |
-| Large | `yolov8l-det-coco.hef` | [Download](https://huggingface.co/EdgeFirst/yolov8-det/resolve/main/hailo/yolov8l-det-coco.hef) |
-| XLarge | `yolov8x-det-coco.hef` | [Download](https://huggingface.co/EdgeFirst/yolov8-det/resolve/main/hailo/yolov8x-det-coco.hef) |
-
-</details>
-
-<details>
-<summary><strong>NVIDIA Jetson</strong> — Jetson FP16 and INT8 engines.</summary>
-
-| Size | File | Download |
-|------|------|----------|
-| Nano | `yolov8n-det-coco.engine` | [Download](https://huggingface.co/EdgeFirst/yolov8-det/resolve/main/jetson/yolov8n-det-coco.engine) |
-| Small | `yolov8s-det-coco.engine` | [Download](https://huggingface.co/EdgeFirst/yolov8-det/resolve/main/jetson/yolov8s-det-coco.engine) |
-| Medium | `yolov8m-det-coco.engine` | [Download](https://huggingface.co/EdgeFirst/yolov8-det/resolve/main/jetson/yolov8m-det-coco.engine) |
-| Large | `yolov8l-det-coco.engine` | [Download](https://huggingface.co/EdgeFirst/yolov8-det/resolve/main/jetson/yolov8l-det-coco.engine) |
-| XLarge | `yolov8x-det-coco.engine` | [Download](https://huggingface.co/EdgeFirst/yolov8-det/resolve/main/jetson/yolov8x-det-coco.engine) |
-
-</details>
 
 
 ---
@@ -189,7 +134,7 @@ gst-launch-1.0 \
   v4l2src device=/dev/video0 ! video/x-raw,width=640,height=480 ! \
   edgefirstcameraadaptor ! \
   tensor_filter framework=tensorflow-lite \
-    model=yolov8n-det-coco-int8.tflite \
+    model=yolov8n-det-coco.tflite \
     custom=Delegate:External,ExtDelegateLib:libvx_delegate.so ! \
   edgefirstdetdecoder ! edgefirstoverlay ! waylandsink
 ```
@@ -199,7 +144,7 @@ gst-launch-1.0 \
 ```bash
 gst-launch-1.0 \
   v4l2src device=/dev/video0 ! video/x-raw,width=640,height=480 ! \
-  hailonet hef-path=yolov8n-det-coco-h8l.hef ! \
+  hailonet hef-path=yolov8n-det-coco.hailo8l.hef ! \
   hailofilter function-name=yolov8_nms ! \
   hailooverlay ! videoconvert ! autovideosink
 ```
@@ -225,7 +170,7 @@ gst-launch-1.0 \
 from edgefirst.hal import Model, TensorImage
 
 # Load model — metadata (labels, decoder config) is embedded in the file
-model = Model("yolov8n-det-coco-int8.tflite")
+model = Model("yolov8n-det-coco.tflite")
 
 # Run inference on an image
 image = TensorImage.from_file("image.jpg")