pub struct TestTensorModel;Expand description
––––– Test model –––––
Trait Implementations§
Source§impl ComputeModel<Tensor<u32, TEST_TENSOR_ELEMENT_COUNT, 2>, Tensor<u32, TEST_TENSOR_ELEMENT_COUNT, 2>> for TestTensorModel
impl ComputeModel<Tensor<u32, TEST_TENSOR_ELEMENT_COUNT, 2>, Tensor<u32, TEST_TENSOR_ELEMENT_COUNT, 2>> for TestTensorModel
Source§fn init(&mut self) -> Result<(), InferenceError>
fn init(&mut self) -> Result<(), InferenceError>
Prepare internal state (allocate work buffers, compile kernels, etc.).
Source§fn infer_one(
&mut self,
inp: &TestTensor,
out: &mut TestTensor,
) -> Result<(), InferenceError>
fn infer_one( &mut self, inp: &TestTensor, out: &mut TestTensor, ) -> Result<(), InferenceError>
Single-item inference (1×1).
Source§fn infer_batch(
&mut self,
inputs: Batch<'_, TestTensor>,
outputs: &mut [TestTensor],
) -> Result<(), InferenceError>
fn infer_batch( &mut self, inputs: Batch<'_, TestTensor>, outputs: &mut [TestTensor], ) -> Result<(), InferenceError>
Optional: batched inference. Default loops
infer_one.Source§fn drain(&mut self) -> Result<(), InferenceError>
fn drain(&mut self) -> Result<(), InferenceError>
Ensure outstanding device work is complete (if any).
Source§fn reset(&mut self) -> Result<(), InferenceError>
fn reset(&mut self) -> Result<(), InferenceError>
Reset internal state to a known baseline (drop caches, etc.).
Source§fn metadata(&self) -> ModelMetadata
fn metadata(&self) -> ModelMetadata
Return model metadata (I/O placement preferences, limits).
Auto Trait Implementations§
impl Freeze for TestTensorModel
impl RefUnwindSafe for TestTensorModel
impl Send for TestTensorModel
impl Sync for TestTensorModel
impl Unpin for TestTensorModel
impl UnsafeUnpin for TestTensorModel
impl UnwindSafe for TestTensorModel
Blanket Implementations§
Source§impl<T> BorrowMut<T> for Twhere
T: ?Sized,
impl<T> BorrowMut<T> for Twhere
T: ?Sized,
Source§fn borrow_mut(&mut self) -> &mut T
fn borrow_mut(&mut self) -> &mut T
Mutably borrows from an owned value. Read more