MCPcopy Index your code
hub / github.com/apache/tvm / test_batch_flatten

Function test_batch_flatten

tests/python/relax/test_codegen_coreml.py:233–244  ·  view source on GitHub ↗
()

Source from the content-addressed store, hash-verified

231
232@requires_coreml_runtime
233def test_batch_flatten():
234 x = relax.Var("x", relax.TensorStructInfo([10, 10, 10], "float32"))
235 bb = relax.BlockBuilder()
236 with bb.function("main", [x]):
237 with bb.dataflow():
238 lv0 = bb.emit(relax.op.nn.batch_flatten(x))
239 gv = bb.emit_output(lv0)
240 bb.emit_func_output(gv)
241 mod = bb.get()
242
243 x_data = tvm.runtime.tensor(np.random.rand(10, 10, 10).astype("float32"), dev)
244 verify(mod, [x_data])
245
246
247@requires_coreml_runtime

Callers

nothing calls this directly

Calls 8

functionMethod · 0.95
dataflowMethod · 0.95
emitMethod · 0.95
emit_outputMethod · 0.95
emit_func_outputMethod · 0.95
getMethod · 0.95
verifyFunction · 0.70
astypeMethod · 0.45

Tested by

no test coverage detected

Used in the wild real call sites across dependent graphs

searching dependent graphs…