def expected():
x = relay.var("x", shape=(1, 32, 56, 56))
w = relay.var("w", shape=(32, 1, 3, 3))
x = relay.layout_transform(x, "NCHW", "NCHW8c")
w = relay.layout_transform(w, "OIHW", "OIHW1i8o")
y = relay.nn.contrib_depthwise_conv2d_nchwc(
x,
w,
padding=(1, 1, 1, 1),
channels=32,
kernel_size=(3, 3),
groups=32,
data_layout="NCHW8c",
kernel_layout="OIHW1i8o",
out_layout="NCHW8c",
)
y = relay.layout_transform(y, "NCHW8c", "NCHW")
y = relay.Function(analysis.free_vars(y), y)
return y
def expected():
x = relay.var("x", shape=(1, 64, 56, 56))
bias = relay.var("bias", shape=(64,))
scale = relay.var("scale", shape=(64, 1, 1))
weight = relay.var("weight")
x = relay.layout_transform(x, "NCHW", "NCHW16c")
bias = relay.expand_dims(bias, 1, 2)
bias = relay.expand_dims(bias, 0, 1)
bias = relay.layout_transform(bias, "NCHW", "NCHW16c")
scale = relay.expand_dims(scale, 0, 1)
scale = relay.layout_transform(scale, "NCHW", "NCHW16c")
y = relay.nn.conv2d(
x, weight, channels=64, kernel_size=(3, 3), padding=(1, 1), data_layout="NCHW16c"
)
y = relay.add(y, bias) # test broadcasting to lhs
y = relay.multiply(scale, y) # test broadcasting to rhs
y = relay.layout_transform(y, "NCHW16c", "NCHW")
y = relay.Function(analysis.free_vars(y), y)
return y
def expected():
x = relay.var("x", shape=(1, 64, 56, 56))
bias = relay.var("bias", shape=(64, ))
weight = relay.var("weight", shape=(64, 64, 3, 3))
y = relay.layout_transform(x, "NCHW", "NCHW16c")
w = relay.layout_transform(weight, "OIHW", "OIHW16i")
y = relay.nn.conv2d(y,
w,
channels=64,
kernel_size=(3, 3),
padding=(1, 1),
kernel_layout="OIHW16i",
data_layout="NCHW16c")
y = relay.nn.max_pool2d(y, pool_size=(2, 2), layout="NCHW16c")
y = relay.layout_transform(y, "NCHW16c", "NCHW")
y = relay.nn.lrn(y)
y = relay.Function(analysis.free_vars(y), y)
return y
def expected():
x = relay.var("x", shape=(1, 64, 56, 56))
weight1 = relay.var("weight1")
weight2 = relay.var("weight2")
y = relay.layout_transform(x, "NCHW", "NCHW16c")
y = relay.nn.conv2d(
y, weight1, channels=32, kernel_size=(3, 3), padding=(1, 1), data_layout="NCHW16c"
)
y = relay.nn.relu(y)
y1 = relay.nn.conv2d(
y, weight2, channels=32, kernel_size=(3, 3), padding=(1, 1), data_layout="NCHW16c"
)
y1 = relay.nn.relu(y1)
y1 = relay.layout_transform(y1, "NCHW16c", "NCHW")
y2 = relay.layout_transform(y, "NCHW16c", "NCHW")
y2 = relay.nn.batch_flatten(y2)
ret = relay.Tuple([y1, y2])
y = relay.Function(analysis.free_vars(ret), ret)
return y
def expected():
x = relay.var("x", shape=(1, 56, 56, 64))
weight1 = relay.var("weight1", shape=(3, 3, 64, 32))
weight2 = relay.var("weight2", shape=(1, 1, 64, 32))
weight1 = relay.layout_transform(weight1, "HWIO", "OIHW")
weight2 = relay.layout_transform(weight2, "HWIO", "OIHW")
x = relay.layout_transform(x, "NHWC", "NCHW")
y = relay.nn.conv2d(x,
weight1,
channels=32,
kernel_size=(3, 3),
padding=(1, 1))
y = relay.nn.relu(y)
y2 = relay.nn.conv2d(x, weight2, channels=32, kernel_size=(1, 1))
y2 = relay.nn.relu(y2)
y = y + y2
y = relay.nn.global_max_pool2d(y)
y = relay.layout_transform(y, "NCHW", "NHWC")
return relay.Function(analysis.free_vars(y), y)
def build_tvm(self, net, torch_inputs):
self.graph_pth = torch2trt.GraphModule(net, torch_inputs)
with torch2trt.core.tvm_network():
trace, graph_pth = torch2trt.core.torch2tvm(
net,
torch_inputs,
input_names=self.input_names,
verbose=self.verbose)
self.refit_weight_dict = graph_pth.refit_weight_dict
input_names = get_torch_forward_name(net.forward)
self.graph_pth = graph_pth
outputs = graph_pth.get_resolved_outputs()
tvm_weight_dict = graph_pth.context.tvm_weight_dict
self.params = {k.name_hint: v for k, v in tvm_weight_dict.items()}
print(len(self.params))
self.graph = expr.Function(analysis.free_vars(outputs), outputs)
if self.graph_post_fn is not None:
self.graph = self.graph_post_fn(self.graph)
self.ctx = TVMInference(self.graph, self.params, input_names=input_names, ctx=tvm.gpu(0), cudnn=True)
def expected_nhwc_int8():
x = relay.var("x", shape=(1, 56, 56, 73), dtype="int8")
weight = relay.var("weight1", shape=(3, 3, 73, 79), dtype="int8")
tile_rows = 4
tile_cols = 16
weight_transformed = relay.nn.contrib_conv2d_gemm_weight_transform(
weight, tile_rows, tile_cols
)
y = relay.nn.contrib_conv2d_gemm_without_weight_transform(
x,
weight_transformed,
channels=79,
kernel_size=(3, 3),
data_layout="NHWC",
kernel_layout="HWIO",
out_dtype="int32",
)
y = relay.Function(analysis.free_vars(y), y)
return y
def before_nhwc():
x = relay.var("x", shape=(1, 56, 56, 64))
weight1 = relay.var('weight1')
weight2 = relay.var('weight2')
y = relay.nn.conv2d(x,
weight1,
channels=32,
kernel_size=(3, 3),
padding=(1, 1),
data_layout='NHWC')
y1 = relay.nn.conv2d(y,
weight2,
channels=32,
kernel_size=(3, 3),
padding=(1, 1),
data_layout='NHWC')
ret = relay.concatenate([y, y1], axis=3)
y = relay.Function(analysis.free_vars(ret), ret)
return y
def expected_nhwc():
x = relay.var("x", shape=(1, 56, 56, 64))
weight1 = relay.var('weight1')
weight2 = relay.var('weight2')
y = relay.layout_transform(x, "NHWC", "NCHW16c")
y = relay.nn.conv2d(y, weight1,
channels=32,
kernel_size=(3, 3),
padding=(1, 1),
data_layout="NCHW16c")
y1 = relay.nn.conv2d(y, weight2,
channels=32,
kernel_size=(3, 3),
padding=(1, 1),
data_layout='NCHW16c')
ret = relay.concatenate([y, y1], axis=1)
ret = relay.layout_transform(ret, "NCHW16c", "NHWC")
y = relay.Function(analysis.free_vars(ret), ret)
return y
def before():
x = relay.var("x", shape=(1, 500, 500, 64))
kernel = relay.var('kernel', shape=(3, 3, 64, 64), dtype='float32')
bias = relay.var("bias", shape=(64, ))
multiplier1 = relay.var('multiplier1', shape=(1, ), dtype='float32')
multiplier2 = relay.var('multiplier2', shape=(1, 1), dtype='float32')
y = relay.nn.conv2d(x,
kernel,
data_layout='NHWC',
kernel_layout="HWIO",
kernel_size=(3, 3))
y = relay.add(bias, y)
y = relay.nn.relu(y)
y = relay.multiply(multiplier1, y)
y = relay.multiply(y, multiplier2)
y = relay.Function(analysis.free_vars(y), y)
return y
def expected():
x = relay.var("x", shape=(1, 56, 56, 64), dtype="int8")
weight1 = relay.var("weight1", shape=(3, 3, 64, 64), dtype="int8")
weight2 = relay.var("weight2", shape=(3, 3, 64, 64), dtype="int8")
weight1 = relay.layout_transform(weight1, "HWIO", "OIHW")
weight2 = relay.layout_transform(weight2, "HWIO", "OIHW")
y = relay.layout_transform(x, "NHWC", "NCHW")
y = relay.qnn.op.conv2d(
y,
weight1,
relay.const(1, "int32"),
relay.const(1, "int32"),
relay.const(1, "float32"),
relay.const(1, "float32"),
channels=64,
kernel_size=(3, 3),
padding=(1, 1),
)
y1 = relay.qnn.op.conv2d(
y,
weight2,
relay.const(1, "int32"),
relay.const(1, "int32"),
relay.const(1, "float32"),
relay.const(1, "float32"),
channels=64,
kernel_size=(3, 3),
padding=(1, 1),
)
y = relay.cast(y, "int8")
y1 = relay.cast(y, "int8")
ret = relay.qnn.op.concatenate(
[y, y1],
[relay.const(1, "float32"), relay.const(1, "float32")],
[relay.const(1, "int32"), relay.const(1, "int32")],
relay.const(1, "float32"),
relay.const(1, "int32"),
axis=1,
)
ret = relay.layout_transform(ret, "NCHW", "NHWC")
y = relay.Function(analysis.free_vars(ret), ret)
return y
def before():
x = relay.var("x", shape=(1, 56, 56, 64), dtype="int8")
weight1 = relay.var("weight1", shape=(3, 3, 64, 64), dtype="int8")
weight2 = relay.var("weight2", shape=(3, 3, 64, 64), dtype="int8")
y = relay.qnn.op.conv2d(
x,
weight1,
relay.const(1, "int32"),
relay.const(1, "int32"),
relay.const(1, "float32"),
relay.const(1, "float32"),
channels=64,
kernel_size=(3, 3),
padding=(1, 1),
data_layout="NHWC",
kernel_layout="HWIO",
)
y1 = relay.qnn.op.conv2d(
y,
weight2,
relay.const(1, "int32"),
relay.const(1, "int32"),
relay.const(1, "float32"),
relay.const(1, "float32"),
channels=64,
kernel_size=(3, 3),
padding=(1, 1),
data_layout="NHWC",
kernel_layout="HWIO",
)
y = relay.cast(y, "int8")
y1 = relay.cast(y, "int8")
ret = relay.qnn.op.concatenate(
[y, y1],
[relay.const(1, "float32"), relay.const(1, "float32")],
[relay.const(1, "int32"), relay.const(1, "int32")],
relay.const(1, "float32"),
relay.const(1, "int32"),
axis=3,
)
y = relay.Function(analysis.free_vars(ret), ret)
return y
def expected():
x = relay.var("x", shape=(1, 56, 56, 64))
bias = relay.var("bias", shape=(64,))
weight = relay.var("weight", shape=(3, 3, 64, 64))
x = relay.layout_transform(x, "NHWC", "NCHW")
weight = relay.layout_transform(weight, "HWIO", "OIHW")
y = relay.nn.conv2d(x, weight, channels=64, kernel_size=(3, 3), padding=(1, 1))
bias = relay.expand_dims(bias, axis=0, num_newaxis=3)
bias = relay.layout_transform(bias, "NHWC", "NCHW")
y = relay.add(y, bias)
# a useless tuple, which will be eliminated
y = relay.Tuple([y])[0]
y = relay.nn.relu(y)
y = relay.nn.max_pool2d(y, pool_size=(2, 2))
y = relay.cast(y, "int32")
y = relay.layout_transform(y, "NCHW", "NHWC")
y = relay.nn.batch_flatten(y)
y = relay.Function(analysis.free_vars(y), y)
return y
def before():
x = relay.var("x", shape=(1, 64, 56, 56))
weight1 = relay.var("weight1", shape=(64, 64, 3, 3))
y = relay.nn.conv2d(
x,
weight1,
channels=64,
kernel_size=(3, 3),
padding=(1, 1),
data_layout="NCHW",
kernel_layout="OIHW",
)
rois = relay.var("rois", shape=(32, 5))
y = relay.vision.roi_pool(y,
rois,
pooled_size=(14, 14),
spatial_scale=0.0625,
layout="NCHW")
y = relay.Function(analysis.free_vars(y), y)
return y
def before():
x = relay.var("x", shape=(1, 56, 56, 64))
bias = relay.var("bias", shape=(64, ))
weight = relay.var("weight", shape=(3, 3, 64, 64))
y = relay.nn.conv2d(x,
weight,
channels=64,
kernel_size=(3, 3),
padding=(1, 1),
data_layout='NHWC',
kernel_layout='HWIO')
y = relay.nn.bias_add(y, bias, axis=3)
# a useless tuple, which will be eliminated
y = relay.Tuple([y])[0]
y = relay.nn.relu(y)
y = relay.nn.max_pool2d(y, pool_size=(2, 2), layout='NHWC')
y = relay.cast(y, 'int32')
y = relay.nn.batch_flatten(y)
y = relay.Function(analysis.free_vars(y), y)
return y
def expected_nhwc():
x = relay.var("x", shape=(1, 56, 56, 64))
weight1 = relay.var('weight1', shape=(3, 3, 64, 64))
weight2 = relay.var('weight2', shape=(3, 3, 64, 64))
y = relay.layout_transform(x, "NHWC", "NCHW")
weight1 = relay.layout_transform(weight1, "HWIO", "OIHW")
weight2 = relay.layout_transform(weight2, "HWIO", "OIHW")
y = relay.nn.conv2d(y, weight1,
channels=64,
kernel_size=(3, 3))
y = relay.nn.relu(y)
y = relay.nn.avg_pool2d(y,
pool_size=(1,1))
y = relay.nn.conv2d(y, weight2,
channels=64,
kernel_size=(3, 3))
y = relay.nn.relu(y)
y = relay.layout_transform(y, "NCHW", "NHWC")
y = relay.Function(analysis.free_vars(y), y)
return y
def before():
x = relay.var("x", shape=(1, 64, 56, 56))
weight1 = relay.var('weight1')
weight2 = relay.var('weight2')
y = relay.nn.conv2d(x,
weight1,
channels=32,
kernel_size=(3, 3),
padding=(1, 1))
y = relay.nn.relu(y)
y1 = relay.nn.conv2d(y,
weight2,
channels=32,
kernel_size=(3, 3),
padding=(1, 1))
y1 = relay.nn.relu(y1)
y2 = relay.nn.batch_flatten(y)
ret = relay.Tuple([y1, y2])
y = relay.Function(analysis.free_vars(ret), ret)
return y
def expected():
x = relay.var("x", shape=(1, 32, 28, 28))
weight = relay.var("weight", shape=(32, 32, 3, 3))
weight = relay.layout_transform(weight, "OIHW", "OIHW4i4o")
x = relay.layout_transform(x, "NCHW", "NCHW4c")
y = relay.op.nn.contrib_conv2d_nchwc(x,
weight,
channels=32,
kernel_size=(3, 3),
padding=(1, 1),
data_layout="NCHW4c")
y = relay.strided_slice(y,
begin=relay.const([0, 4], "int32"),
end=relay.const([1, 21], "int32"),
strides=relay.const([1, 1], "int32"))
y = relay.layout_transform(y, "NCHW4c", "NCHW")
y = relay.Function(analysis.free_vars(y), y)
return y
def run_infer_type(expr, mod=None):
if not mod:
mod = tvm.IRModule.from_expr(expr)
mod = transform.InferType()(mod)
entry = mod["main"]
return entry if isinstance(expr, relay.Function) else entry.body
else:
if isinstance(expr, relay.GlobalVar):
gv = expr.name_hint
else:
func = expr
if not isinstance(expr, relay.Function):
func = relay.Function(analysis.free_vars(expr), expr)
mod["main"] = func
gv = "main"
mod = transform.InferType()(mod)
if isinstance(expr, (relay.GlobalVar, relay.Function)):
return mod[gv]
return mod[gv].body
def expected():
x = relay.var("x", shape=(1, 64, 56, 56))
weight1 = relay.var('weight1')
weight2 = relay.var('weight2')
x = relay.layout_transform(x, "NCHW", "NCHW16c")
y = relay.nn.conv2d(x, weight1,
channels=32,
kernel_size=(3, 3),
padding=(1, 1),
data_layout="NCHW16c")
y = relay.nn.relu(y)
y2 = relay.nn.conv2d(x, weight2,
channels=32,
kernel_size=(1, 1),
data_layout='NCHW16c')
y2 = relay.nn.relu(y2)
y = y + y2
y = relay.nn.global_max_pool2d(y, layout="NCHW16c")
y = relay.layout_transform(y, "NCHW16c", "NCHW")
return relay.Function(analysis.free_vars(y), y)
def expected():
x = relay.var("x", shape=(1, 64, 56, 56))
weight1 = relay.var("weight1", shape=(64, 3, 3, 64))
weight2 = relay.var("weight2", shape=(64, 3, 3, 64), dtype='int8')
weight3 = relay.var("weight3", shape=(64, 3, 3, 64))
x = relay.layout_transform(x, 'NCHW', 'NHWC')
weight1 = relay.layout_transform(weight1, 'OHWI', 'HWIO')
out = relay.nn.conv2d(x,
weight1,
channels=64,
kernel_size=(3, 3),
padding=(1, 1),
data_layout='NHWC',
kernel_layout='HWIO')
out = relay.cast(out, 'int8')
out = relay.layout_transform(out, 'NHWC', 'NCHW')
weight2 = relay.layout_transform(weight2, 'OHWI', 'OIHW')
out = relay.qnn.op.conv2d(out,
weight2,
relay.const(1, 'int32'),
relay.const(1, 'int32'),
relay.const(1, 'float32'),
relay.const(1, 'float32'),
channels=64,
kernel_size=(3, 3),
padding=(1, 1),
data_layout='NCHW',
kernel_layout='OIHW')
out = relay.cast(out, 'float32')
out = relay.layout_transform(out, 'NCHW', 'NHWC')
weight3 = relay.layout_transform(weight3, 'OHWI', 'HWIO')
out = relay.nn.conv2d_transpose(out,
weight3,
channels=64,
kernel_size=(3, 3),
padding=(1, 1),
data_layout='NHWC',
kernel_layout='HWIO')
out = relay.layout_transform(out, 'NHWC', 'NCHW')
out = relay.Function(analysis.free_vars(out), out)
return out
def expected():
x = relay.var("x", shape=(1, 64, 56, 56))
weight1 = relay.var("weight1", shape=(64, 64, 3, 3))
x = relay.layout_transform(x, "NCHW", "NHWC")
weight1 = relay.layout_transform(weight1, "OIHW", "HWIO")
y = relay.nn.conv2d(
x,
weight1,
channels=64,
kernel_size=(3, 3),
padding=(1, 1),
data_layout="NHWC",
kernel_layout="HWIO",
)
y = relay.layout_transform(y, "NHWC", "NCHW")
rois = relay.var("rois", shape=(32, 5))
y = relay.vision.roi_align(
y, rois, pooled_size=(14, 14), spatial_scale=0.0625, sample_ratio=2, layout="NCHW"
)
y = relay.Function(analysis.free_vars(y), y)
return y
def before():
x = relay.var("x", shape=(1, 56, 56, 64))
weight1 = relay.var("weight1", shape=(3, 3, 64, 32))
weight2 = relay.var("weight2", shape=(1, 1, 64, 32))
y = relay.nn.conv2d(
x,
weight1,
channels=32,
kernel_size=(3, 3),
padding=(1, 1),
data_layout="NHWC",
kernel_layout="HWIO",
)
y = relay.nn.relu(y)
y2 = relay.nn.conv2d(
x, weight2, channels=32, kernel_size=(1, 1), data_layout="NHWC", kernel_layout="HWIO"
)
y2 = relay.nn.relu(y2)
y = y + y2
y = relay.nn.global_max_pool2d(y, layout="NHWC")
return relay.Function(analysis.free_vars(y), y)
def expected():
x = relay.var("x", shape=(1, 56, 56, 64))
weight1 = relay.var("weight1", shape=(3, 3, 64, 64))
weight2 = relay.var("weight2", shape=(3, 3, 64, 64))
weight1 = relay.layout_transform(weight1, "HWIO", "OIHW")
weight2 = relay.layout_transform(weight2, "HWIO", "OIHW")
y = relay.layout_transform(x, "NHWC", "NCHW")
y = relay.nn.conv2d(y,
weight1,
channels=64,
kernel_size=(3, 3),
padding=(1, 1))
y1 = relay.nn.conv2d(y,
weight2,
channels=64,
kernel_size=(3, 3),
padding=(1, 1))
ret = relay.concatenate([y, y1], axis=1)
ret = relay.layout_transform(ret, "NCHW", "NHWC")
y = relay.Function(analysis.free_vars(ret), ret)
return y
def before_nhwc():
x = relay.var("x", shape=(1, 56, 56, 64))
weight1 = relay.var('weight1', shape=(3, 3, 64, 64))
weight2 = relay.var('weight2', shape=(3, 3, 64, 64))
y = relay.nn.conv2d(x,
weight1,
channels=64,
kernel_size=(3, 3),
data_layout='NHWC',
kernel_layout='HWIO')
y = relay.nn.relu(y)
y = relay.nn.avg_pool2d(y, pool_size=(1, 1), layout='NHWC')
y = relay.nn.conv2d(y,
weight2,
channels=64,
kernel_size=(3, 3),
data_layout='NHWC',
kernel_layout='HWIO')
y = relay.nn.relu(y)
y = relay.Function(analysis.free_vars(y), y)
return y
def before():
x = relay.var("x", shape=(1, 64, 56, 56))
weight1 = relay.var("weight1", shape=(64, 3, 3, 64))
weight2 = relay.var("weight2", shape=(64, 3, 3, 64), dtype="int8")
weight3 = relay.var("weight3", shape=(64, 3, 3, 64))
out = relay.nn.conv2d(
x,
weight1,
channels=64,
kernel_size=(3, 3),
padding=(1, 1),
data_layout="NCHW",
kernel_layout="OHWI",
)
out = relay.cast(out, "int8")
out = relay.qnn.op.conv2d(
out,
weight2,
relay.const(1, "int32"),
relay.const(1, "int32"),
relay.const(1, "float32"),
relay.const(1, "float32"),
channels=64,
kernel_size=(3, 3),
padding=(1, 1),
data_layout="NCHW",
kernel_layout="OHWI",
)
out = relay.cast(out, "float32")
out = relay.nn.conv2d_transpose(
out,
weight3,
channels=64,
kernel_size=(3, 3),
padding=(1, 1),
data_layout="NCHW",
kernel_layout="OHWI",
)
out = relay.Function(analysis.free_vars(out), out)
return out
def before():
x = relay.var("x", shape=(1, 56, 56, 64))
weight = relay.var("weight", shape=(3, 3, 64, 16))
bias = relay.var("bias", shape=(1, 1, 1, 16))
y = relay.nn.conv2d(
x,
weight,
channels=16,
kernel_size=(3, 3),
padding=(1, 1),
data_layout="NHWC",
kernel_layout="HWIO",
)
y = relay.add(y, bias)
mean = relay.mean(y, axis=3, exclude=True)
var = relay.variance(y, axis=3, exclude=True)
gamma = relay.var("gamma")
beta = relay.var("beta")
y = relay.nn.batch_norm(y, gamma, beta, mean, var, axis=3)
y = y[0]
y = relay.Function(analysis.free_vars(y), y)
return y
def expected():
x = relay.var("x", shape=(1, 56, 56, 64))
weight = relay.var("weight", shape=(3, 3, 64, 16))
bias = relay.var("bias", shape=(1, 1, 1, 16))
x = relay.layout_transform(x, src_layout="NHWC", dst_layout="NCHW")
x = relay.layout_transform(x, src_layout="NCHW", dst_layout="NCHW16c")
weight = relay.layout_transform(weight, src_layout="HWIO", dst_layout="OIHW")
y = relay.nn.conv2d(
x, weight, channels=16, kernel_size=(3, 3), padding=(1, 1), data_layout="NCHW16c"
)
bias = relay.layout_transform(bias, src_layout="NHWC", dst_layout="NCHW")
bias = relay.layout_transform(bias, src_layout="NCHW", dst_layout="NCHW16c")
add = relay.add(y, bias)
y = relay.layout_transform(add, src_layout="NCHW16c", dst_layout="NCHW")
y = relay.layout_transform(y, src_layout="NCHW", dst_layout="NHWC")
mean = relay.mean(y, axis=3, exclude=True)
var = relay.variance(y, axis=3, exclude=True)
denom = relay.const(1.0) / relay.sqrt(var + relay.const(1e-05))
gamma = relay.var("gamma", shape=(16,))
denom = denom * gamma
denom_expand1 = relay.expand_dims(denom, axis=1, num_newaxis=2)
denom_expand2 = relay.expand_dims(denom_expand1, axis=0)
denom_nchwc16 = relay.layout_transform(
denom_expand2, src_layout="NCHW", dst_layout="NCHW16c"
)
out = add * denom_nchwc16
beta = relay.var("beta", shape=(16,))
numerator = (-mean) * denom + beta
numerator_expand1 = relay.expand_dims(numerator, axis=1, num_newaxis=2)
numerator_expand2 = relay.expand_dims(numerator_expand1, axis=0)
numerator_nchwc16 = relay.layout_transform(
numerator_expand2, src_layout="NCHW", dst_layout="NCHW16c"
)
out = out + numerator_nchwc16
out = relay.layout_transform(out, src_layout="NCHW16c", dst_layout="NCHW")
y = relay.layout_transform(out, src_layout="NCHW", dst_layout="NHWC")
y = relay.Function(analysis.free_vars(y), y)
return y
def before():
x = relay.var("x", shape=(1, 56, 56, 64), dtype='int8')
weight1 = relay.var('weight1', shape=(3, 3, 64, 64), dtype='int8')
weight2 = relay.var('weight2', shape=(3, 3, 64, 64), dtype='int8')
y = relay.qnn.op.conv2d(x,
weight1,
relay.const(1, 'int32'),
relay.const(1, 'int32'),
relay.const(1, 'float32'),
relay.const(1, 'float32'),
channels=64,
kernel_size=(3, 3),
padding=(1, 1),
data_layout='NHWC',
kernel_layout='HWIO')
y1 = relay.qnn.op.conv2d(y,
weight2,
relay.const(1, 'int32'),
relay.const(1, 'int32'),
relay.const(1, 'float32'),
relay.const(1, 'float32'),
channels=64,
kernel_size=(3, 3),
padding=(1, 1),
data_layout='NHWC',
kernel_layout='HWIO')
y = relay.cast(y, 'int8')
y1 = relay.cast(y, 'int8')
ret = relay.qnn.op.concatenate(
[y, y1], [relay.const(1, 'float32'),
relay.const(1, 'float32')],
[relay.const(1, 'int32'),
relay.const(1, 'int32')],
relay.const(1, 'float32'),
relay.const(1, 'int32'),
axis=3)
y = relay.Function(analysis.free_vars(ret), ret)
return y
def expected():
x = relay.var("x", shape=(1, 56, 56, 64), dtype='int8')
weight1 = relay.var('weight1', shape=(3, 3, 64, 64), dtype='int8')
weight2 = relay.var('weight2', shape=(3, 3, 64, 64), dtype='int8')
weight1 = relay.layout_transform(weight1, 'HWIO', 'OIHW')
weight2 = relay.layout_transform(weight2, 'HWIO', 'OIHW')
y = relay.layout_transform(x, "NHWC", "NCHW")
y = relay.qnn.op.conv2d(y,
weight1,
relay.const(1, 'int32'),
relay.const(1, 'int32'),
relay.const(1, 'float32'),
relay.const(1, 'float32'),
channels=64,
kernel_size=(3, 3),
padding=(1, 1))
y1 = relay.qnn.op.conv2d(y,
weight2,
relay.const(1, 'int32'),
relay.const(1, 'int32'),
relay.const(1, 'float32'),
relay.const(1, 'float32'),
channels=64,
kernel_size=(3, 3),
padding=(1, 1))
y = relay.cast(y, 'int8')
y1 = relay.cast(y, 'int8')
ret = relay.qnn.op.concatenate(
[y, y1], [relay.const(1, 'float32'),
relay.const(1, 'float32')],
[relay.const(1, 'int32'),
relay.const(1, 'int32')],
relay.const(1, 'float32'),
relay.const(1, 'int32'),
axis=1)
ret = relay.layout_transform(ret, "NCHW", "NHWC")
y = relay.Function(analysis.free_vars(ret), ret)
return y
