Upload README.md with huggingface_hub

README.md

@@ -93,8 +93,30 @@ for n, frame in enumerate(video_frames, start=1):   # frame: [1,3,172,172], RGB,
 print("top-1:", int(logits.argmax()))
 ```
 
-A full Kotlin implementation (camera → per-frame → top-5) is in the sample app's
-`ActionRecognizer.kt`.
+### Kotlin (Android, LiteRT CompiledModel GPU)
+
+```kotlin
+val options = CompiledModel.Options(Accelerator.GPU)
+val model = CompiledModel.create(context.assets, "movinet_a0_stream.tflite", options, null)
+val inBufs = model.createInputBuffers()    // [0]=frame, [1..28]=stream, [29..44]=pool sums, [45]=inv_count, [46]=1.0
+val outBufs = model.createOutputBuffers()  // [0]=logits, [1..11]=current frames, [12..27]=fresh means
+
+inBufs[46].writeFloat(floatArrayOf(1f))    // constant decoupler
+// reset recurrent state (zeros) at the start of a clip; keep host-side stream buffers + pool sums
+
+for ((n, frameNCHW) in videoFrames.withIndex()) {           // frame: [1,3,172,172], RGB, 0..1
+    inBufs[0].writeFloat(frameNCHW)
+    inBufs[45].writeFloat(floatArrayOf(1f / (n + 1)))       // inv_count
+    // (stream inputs 1..28 and pool inputs 29..44 already staged from the previous frame)
+    model.run(inBufs, outBufs)
+    val logits = outBufs[0].readFloat()                     // [600] Kinetics-600
+    // host-side: shift each stream buffer with the emitted current frame (outBufs[1..11]),
+    // and accumulate poolSum[i] += outBufs[12+i], then write both back to inBufs for the next frame.
+}
+```
+
+A full implementation (camera → per-frame → top-5, with the host-side shift register and pool
+accumulation) is in the sample app's `ActionRecognizer.kt`.
 
 ## Conversion