def verify_UpsampleLayerParams(input_dim, scale, mode):
dtype = "float32"
a_np = np.full(input_dim, 1, dtype=dtype)
if mode == 'NN':
b_np = topi.testing.upsampling_python(a_np, scale)
else:
new_h = input_dim[2] * scale
new_w = input_dim[3] * scale
b_np = topi.testing.bilinear_resize_python(a_np, (new_h, new_w), 'NCHW')
input = [('input', datatypes.Array(*input_dim))]
output = [('output', datatypes.Array(*b_np.shape))]
builder = NeuralNetworkBuilder(input, output)
builder.add_upsample(name='Upsample',
scaling_factor_h=scale,
scaling_factor_w=scale,
mode=mode,
input_name='input',
output_name='output')
model = cm.models.MLModel(builder.spec)
for target, ctx in ctx_list():
out = run_tvm_graph(model, target, ctx, a_np, 'input', b_np.shape, dtype)
tvm.testing.assert_allclose(out, b_np, rtol=1e-5)
def verify_UpsampleLayerParams(input_dim, scale, mode):
dtype = "float32"
a_np = np.full(input_dim, 1, dtype=dtype)
if mode == "NN":
b_np = tvm.topi.testing.upsampling_python(a_np, (scale, scale))
else:
new_h = input_dim[2] * scale
new_w = input_dim[3] * scale
b_np = tvm.topi.testing.bilinear_resize_python(a_np, (new_h, new_w), "NCHW")
input = [("input", datatypes.Array(*input_dim))]
output = [("output", datatypes.Array(*b_np.shape))]
builder = NeuralNetworkBuilder(input, output)
builder.add_upsample(
name="Upsample",
scaling_factor_h=scale,
scaling_factor_w=scale,
mode=mode,
input_name="input",
output_name="output",
)
model = cm.models.MLModel(builder.spec)
for target, dev in tvm.testing.enabled_targets():
out = run_tvm_graph(model, target, dev, a_np, "input", b_np.shape, dtype)
tvm.testing.assert_allclose(out, b_np, rtol=1e-5)
def verify_UpsampleLayerParams(input_dim, scale, mode):
dtype = "float32"
a_np = np.full(input_dim, 1, dtype=dtype)
if mode == 'NN':
b_np = topi.testing.upsampling_python(a_np, scale)
else:
new_h = input_dim[2] * scale
new_w = input_dim[3] * scale
b_np = topi.testing.bilinear_resize_python(a_np, (new_h, new_w), 'NCHW')
input = [('input', datatypes.Array(*input_dim))]
output = [('output', datatypes.Array(*b_np.shape))]
builder = NeuralNetworkBuilder(input, output)
builder.add_upsample(name='Upsample',
scaling_factor_h=scale,
scaling_factor_w=scale,
mode=mode,
input_name='input',
output_name='output')
model = cm.models.MLModel(builder.spec)
for target, ctx in ctx_list():
out = run_tvm_graph(model, a_np, 'input', b_np.shape, dtype)
tvm.testing.assert_allclose(out, b_np, rtol=1e-5)
def verify_UpsampleLayerParams(input_dim, scale, mode):
dtype = "float32"
a_np = np.full(input_dim, 1, dtype=dtype)
if mode == "NN":
method = "nearest_neighbor"
coord_trans = "asymmetric"
else:
method = "linear"
coord_trans = "align_corners"
b_np = tvm.topi.testing.resize2d_python(a_np, (scale, scale), "NCHW", method, coord_trans)
input = [("input", datatypes.Array(*input_dim))]
output = [("output", datatypes.Array(*b_np.shape))]
builder = NeuralNetworkBuilder(input, output)
builder.add_upsample(
name="Upsample",
scaling_factor_h=scale,
scaling_factor_w=scale,
mode=mode,
input_name="input",
output_name="output",
)
model = cm.models.MLModel(builder.spec)
for target, dev in tvm.testing.enabled_targets():
out = run_tvm_graph(model, target, dev, a_np, "input", b_np.shape, dtype)
tvm.testing.assert_allclose(out, b_np, rtol=1e-5)
def test_upsample_converter(self):
input_dim = (1, 1, 1)
output_dim = (1, 2, 2)
input = [('input', datatypes.Array(*input_dim))]
output = [('output', datatypes.Array(*output_dim))]
builder = NeuralNetworkBuilder(input, output)
builder.add_upsample(name='Upsample', scaling_factor_h=2, scaling_factor_w=2, input_name='input',
output_name='output')
model_onnx = convert_coreml(builder.spec)
self.assertTrue(model_onnx is not None)
def test_upsample_converter(self):
input_dim = (1, 1, 1)
output_dim = (1, 2, 2)
input = [('input', datatypes.Array(*input_dim))]
output = [('output', datatypes.Array(*output_dim))]
builder = NeuralNetworkBuilder(input, output)
builder.add_upsample(name='Upsample',
scaling_factor_h=2,
scaling_factor_w=2,
input_name='input',
output_name='output')
context = ConvertContext()
node = UpsampleLayerConverter.convert(
context, builder.spec.neuralNetwork.layers[0], ['input'],
['output'])
self.assertTrue(node is not None)