def test_repeat(self):
c = relay.expr.const(np.ones((2, 2), dtype=np.float32))
net = relay.repeat(c, repeats=2, axis=0)
net = relay.Function([], net)
mod = tvm.IRModule.from_expr(net)
mod = relay.transform.InferType()(mod)
xgraph = xf_relay.from_relay(mod, {})
layers = xgraph.get_layers()
assert layers[0].type[0] == "Constant"
assert layers[1].type[0] == "AnyOp"
assert layers[1].shapes == [8]
c = relay.expr.const(np.ones((2, 2), dtype=np.float32))
net = relay.repeat(c, repeats=2, axis=1)
net = relay.Function([], net)
mod = tvm.IRModule.from_expr(net)
mod = relay.transform.InferType()(mod)
xgraph = xf_relay.from_relay(mod, {})
layers = xgraph.get_layers()
assert layers[0].type[0] == "Constant"
assert layers[1].type[0] == "AnyOp"
assert layers[1].shapes == [2, 4]
def test_slice_like(self):
data = relay.expr.const(np.ones((1, 6, 4, 4), np.float32))
sl = relay.expr.const(np.ones((1, 4, 3, 3), np.float32))
net = relay.slice_like(data, sl)
net = relay.Function([], net)
mod = tvm.IRModule.from_expr(net)
mod = relay.transform.InferType()(mod)
xgraph = xf_relay.from_relay(mod, {})
layers = xgraph.get_layers()
assert layers[0].type[0] == "Constant"
assert layers[1].type[0] == "Constant"
assert layers[2].type[0] == "AnyOp"
assert layers[2].shapes == [1, 4, 3, 3]
data = relay.expr.const(np.ones((1, 6, 4, 4), np.float32))
sl = relay.expr.const(np.ones((1, 4, 3, 3), np.float32))
net = relay.slice_like(data, sl, axes=(2, 3))
net = relay.Function([], net)
mod = tvm.IRModule.from_expr(net)
mod = relay.transform.InferType()(mod)
xgraph = xf_relay.from_relay(mod, {})
layers = xgraph.get_layers()
assert layers[0].type[0] == "Constant"
assert layers[1].type[0] == "Constant"
assert layers[2].type[0] == "AnyOp"
assert layers[2].shapes == [1, 6, 3, 3]
def test_relay_op(self):
data = relay.var("data", relay.TensorType((-1, 4, 2, 2), "float32"))
net = relay.std(data, axis=1, keepdims=False, exclude=False)
net = relay.Function(relay.analysis.free_vars(net), net)
mod = tvm.IRModule.from_expr(net)
mod = relay.transform.InferType()(mod)
xgraph = xf_relay.from_relay(mod, {})
layers = xgraph.get_layers()
assert layers[0].type[0] == "Input"
assert layers[1].type[0] == "Mean"
assert layers[1].shapes == [-1, 1, 2, 2]
# assert isinstance(layers[1].attrs['relay_id'], list)
assert layers[1].attrs["axes"] == [1]
assert layers[1].attrs["keepdims"] is True
assert layers[2].type[0] == "RelayOp"
assert layers[2].shapes == [-1, 2, 2]
# assert isinstance(layers[2].attrs['relay_id'], list)
assert layers[2].attrs["relay_shape"] == [-1, 2, 2]
assert layers[2].attrs["dtype"] == "float32"
assert layers[2].attrs["axis"] == "[1]"
assert layers[2].attrs["keepdims"] == "0"
assert layers[2].attrs["exclude"] == "0"
assert layers[3].type[0] == "Sqrt"
assert layers[3].shapes == [-1, 2, 2]
def test_relay_op(self):
data = relay.var("data", relay.TensorType((-1, 4, 2, 2), "float32"))
net = relay.std(data, axis=1, keepdims=False, exclude=False)
net = relay.Function(relay.analysis.free_vars(net), net)
mod = tvm.IRModule.from_expr(net)
mod = relay.transform.InferType()(mod)
xgraph = xf_relay.from_relay(mod, {})
layers = xgraph.get_layers()
assert layers[0].type[0] == 'Input'
assert layers[1].type[0] == 'Mean'
assert layers[1].shapes == [-1, 1, 2, 2]
# assert isinstance(layers[1].attrs['relay_id'], list)
assert layers[1].attrs['axes'] == [1]
assert layers[1].attrs['keepdims'] is True
assert layers[2].type[0] == 'RelayOp'
assert layers[2].shapes == [-1, 2, 2]
# assert isinstance(layers[2].attrs['relay_id'], list)
assert layers[2].attrs['relay_shape'] == [-1, 2, 2]
assert layers[2].attrs['dtype'] == 'float32'
assert layers[2].attrs['axis'] == '[1]'
assert layers[2].attrs['keepdims'] == '0'
assert layers[2].attrs['exclude'] == '0'
assert layers[3].type[0] == 'Sqrt'
assert layers[3].shapes == [-1, 2, 2]
def test_split_tuple(self):
data = relay.var("data", relay.TensorType((-1, 5, 4, 4), "float32"))
net = relay.split(data, indices_or_sections=(1, 4), axis=1)\
.astuple()
net = relay.Function([data], net)
mod = tvm.IRModule.from_expr(net)
mod = relay.transform.InferType()(mod)
xgraph = xf_relay.from_relay(mod, {})
layers = xgraph.get_layers()
assert layers[0].type[0] == 'Input'
assert layers[1].type[0] == 'Split'
assert 'relay_id' in layers[1].attrs
assert layers[1].attrs['axis'] == 1
assert layers[1].attrs['indices'] == (1, 4)
assert layers[1].shapes == TupleShape([
TensorShape([-1, 1, 4, 4]),
TensorShape([-1, 3, 4, 4]),
TensorShape([-1, 1, 4, 4])
])
def test_resnet_block(self):
data = relay.var("data", relay.TensorType((-1, 3, 224, 224),
"float32"))
weight = relay.var("weight")
bn_gamma = relay.var("bn_gamma")
bn_beta = relay.var("bn_beta")
bn_mmean = relay.var("bn_mean")
bn_mvar = relay.var("bn_var")
conv2d0_expr = relay.nn.conv2d(data=data,
weight=weight,
kernel_size=(3, 3),
channels=16,
padding=(1, 1))
bn0_expr = relay.nn.batch_norm(conv2d0_expr, bn_gamma, bn_beta,
bn_mmean, bn_mvar)[0]
relu0_expr = relay.nn.relu(bn0_expr)
max_pool0_expr = relay.nn.max_pool2d(relu0_expr,
pool_size=(2, 2),
strides=(2, 2))
conv2d1_weight = relay.var("conv2d1_weight")
conv2d1_bias = relay.var("conv2d1_bias")
conv2d1_expr = relay.nn.conv2d(data=max_pool0_expr,
weight=conv2d1_weight,
kernel_size=(3, 3),
channels=16,
padding=(1, 1))
bias_add0_expr = relay.nn.bias_add(conv2d1_expr, conv2d1_bias, axis=1)
relu1_expr = relay.nn.relu(bias_add0_expr)
add0_expr = relay.op.tensor.add(max_pool0_expr, relu1_expr)
avg_pool0_expr = relay.nn.avg_pool2d(add0_expr,
pool_size=(2, 2),
strides=(2, 2))
global_avg_pool0_expr = relay.op.nn.global_avg_pool2d(avg_pool0_expr)
bf_expr = relay.nn.batch_flatten(global_avg_pool0_expr)
net = avg_pool0_expr
net = relay.Function(relay.analysis.free_vars(net), net)
mod, params = testing.create_workload(net)
xgraph = xf_relay.from_relay(mod, params)
layers = xgraph.get_layers()
assert (layers[0].type[0] == 'Input')
assert (layers[1].type[0] == 'Convolution')
assert (layers[2].type[0] == 'BatchNorm')
assert (layers[3].type[0] == 'ReLU')
assert (layers[4].type[0] == 'Pooling')
assert (layers[5].type[0] == 'Convolution')
assert (layers[6].type[0] == 'BiasAdd')
assert (layers[7].type[0] == 'ReLU')
assert (layers[8].type[0] == 'Eltwise')
assert (layers[9].type[0] == 'Pooling')
assert (layers[9].shapes == [-1, 16, 56, 56])
def test_add(self):
left = relay.var("left", relay.TensorType((-1, 4, 2, 2), "float32"))
right = relay.expr.const(np.zeros((2, 2), dtype=np.float32))
net = relay.add(left, right)
net = relay.Function([left], net)
mod = tvm.IRModule.from_expr(net)
mod = relay.transform.InferType()(mod)
xgraph = xf_relay.from_relay(mod, {})
layers = xgraph.get_layers()
assert layers[0].type[0] == 'Input'
assert 'relay_id' in layers[0].attrs
assert layers[1].type[0] == 'Constant'
assert layers[1].tops[0][:3] == 'add'
assert 'relay_id' in layers[1].attrs
assert layers[2].type[0] == 'Add'
assert layers[2].shapes == [-1, 4, 2, 2]
assert 'relay_id' in layers[2].attrs
def test_multiply(self):
left = relay.var("left", relay.TensorType((-1, 4, 2, 2), "float32"))
right = relay.var("right", relay.TensorType((-1, 4, 2, 2), "float32"))
net = relay.multiply(left, right)
net = relay.Function([left, right], net)
mod = tvm.IRModule.from_expr(net)
mod = relay.transform.InferType()(mod)
xgraph = xf_relay.from_relay(mod, {})
layers = xgraph.get_layers()
assert layers[0].type[0] == 'Input'
assert 'relay_id' in layers[0].attrs
assert layers[1].type[0] == 'Input'
assert 'relay_id' in layers[1].attrs
assert layers[2].type[0] == 'Multiply'
assert layers[2].shapes == [-1, 4, 2, 2]
assert 'relay_id' in layers[1].attrs
def test_batch_norm(self):
var = relay.var("var", relay.TensorType((-1, 4, 2, 2), "float32"))
data_mean = relay.expr.const(np.zeros((4, ), dtype=np.float32))
data_var = relay.expr.const(np.ones((4, ), dtype=np.float32))
gamma = relay.expr.const(2. * np.ones((4, ), dtype=np.float32))
beta = relay.expr.const(3. * np.ones((4, ), dtype=np.float32))
bn = relay.nn.batch_norm(var, gamma, beta, data_mean, data_var)[0]
# tgi = relay.TupleGetItem(bn, 0)
func = relay.Function([var], bn)
mod = tvm.IRModule.from_expr(func)
mod = relay.transform.InferType()(mod)
xg = xf_relay.from_relay(mod, {})
layers = xg.get_layers()
assert len(layers) == 2
assert layers[0].type[0] == 'Input'
assert 'relay_id' in layers[0].attrs
bnl = layers[1]
assert bnl.type[0] == 'BatchNorm'
assert bnl.shapes == [-1, 4, 2, 2]
np.testing.assert_array_equal(bnl.data[0],
np.zeros((4, ), dtype=np.float32))
np.testing.assert_array_equal(bnl.data[1],
np.ones((4, ), dtype=np.float32))
np.testing.assert_array_equal(bnl.data[2], 2. * np.ones(
(4, ), dtype=np.float32))
np.testing.assert_array_equal(bnl.data[3], 3. * np.ones(
(4, ), dtype=np.float32))
assert 'relay_id' in bnl.attrs
assert bnl.attrs['axis'] == 1
def test_tuple_get_item(self):
var1 = relay.var("var1", relay.TensorType((-1, 4, 2, 2), "int64"))
var2 = relay.var("var2", relay.TensorType((-1, 3, 2, 2), "int64"))
t = relay.Tuple([var1, var2])
tgi = relay.TupleGetItem(t, 0)
net = relay.Function([var1, var2], tgi)
mod = tvm.IRModule.from_expr(net)
mod = relay.transform.InferType()(mod)
xg = xf_relay.from_relay(mod, {})
layers = xg.get_layers()
assert len(layers) == 4
assert layers[0].type[0] == "Input"
assert isinstance(layers[0].attrs["dtype"], str)
assert layers[0].attrs["dtype"] == "int64"
assert "relay_id" in layers[0].attrs
assert layers[1].type[0] == "Input"
assert isinstance(layers[0].attrs["dtype"], str)
assert layers[0].attrs["dtype"] == "int64"
assert "relay_id" in layers[0].attrs
assert layers[2].type[0] == "Tuple"
assert layers[2].shapes == TupleShape([[-1, 4, 2, 2], [-1, 3, 2, 2]])
assert layers[3].type[0] == "TupleGetItem"
assert layers[3].attrs["index"] == 0
assert layers[3].shapes == TensorShape([-1, 4, 2, 2])
def test_arange_full_and_reshape(self):
start = relay.expr.const(0.0)
stop = relay.expr.const(10.0)
step = relay.expr.const(1.0)
fill_val = relay.expr.const(1.0)
fill_shape = [10, 1]
dtype = "float32"
left = relay.arange(start, stop, step, dtype)
left = relay.reshape(left, [-1, 1])
left = relay.reshape(left, [1, -1])
right = relay.full(fill_val, fill_shape, dtype)
right = relay.reshape(right, [1, -1])
net = relay.multiply(left, right)
mod = tvm.IRModule.from_expr(net)
params = {}
xgraph = xf_relay.from_relay(mod, params)
layers = xgraph.get_layers()
assert len(layers) == 10
assert layers[0].type[0] == "Constant"
assert layers[3].type[0] == "AnyOp"
assert layers[7].type[0] == "AnyOp"
assert layers[5].shapes == [1, 10]
assert layers[8].shapes == [1, 10]
def test_tuple(self):
var1 = relay.var("var1", relay.TensorType((-1, 4, 2, 2), "int64"))
var2 = relay.var("var2", relay.TensorType((-1, 3, 2, 2), "int64"))
t = relay.Tuple([var1, var2])
net = relay.Function([var1, var2], t)
mod = tvm.IRModule.from_expr(net)
mod = relay.transform.InferType()(mod)
xg = xf_relay.from_relay(mod, {})
layers = xg.get_layers()
assert layers[0].type[0] == 'Input'
assert isinstance(layers[0].attrs['dtype'], str)
assert layers[0].attrs['dtype'] == 'int64'
assert 'relay_id' in layers[0].attrs
assert layers[1].type[0] == 'Input'
assert isinstance(layers[0].attrs['dtype'], str)
assert layers[0].attrs['dtype'] == 'int64'
assert 'relay_id' in layers[0].attrs
assert layers[2].type[0] == 'Tuple'
assert layers[2].shapes == TupleShape([[-1, 4, 2, 2], [-1, 3, 2, 2]])
def test_avg_pool2d(self):
var = relay.var("var", relay.TensorType((-1, 2, 5, 5), "float32"))
avg_pool = relay.nn.avg_pool2d(var,
pool_size=(3, 3),
strides=(2, 2),
padding=(1, 1),
ceil_mode=True,
count_include_pad=True)
func = relay.Function([var], avg_pool)
mod = tvm.IRModule.from_expr(func)
mod = relay.transform.InferType()(mod)
xg = xf_relay.from_relay(mod, {})
layers = xg.get_layers()
assert len(layers) == 2
assert layers[0].type[0] == 'Input'
assert 'relay_id' in layers[0].attrs
X = layers[1]
assert X.type[0] == 'Pooling'
assert X.shapes == [-1, 2, 3, 3]
assert 'relay_id' in X.attrs
assert X.attrs['padding'] == [[0, 0], [0, 0], [1, 1], [1, 1]]
assert X.attrs['insize'] == [5, 5]
assert X.attrs['outsize'] == [3, 3]
assert X.attrs['data_layout'] == 'NCHW'
assert X.attrs['strides'] == [2, 2]
assert X.attrs['kernel_size'] == [3, 3]
assert X.attrs['pool_type'] == 'Avg'
def test_conv2d(self):
data = relay.var("data", relay.TensorType((-1, 1, 4, 4), "float32"))
weight = relay.expr.const(np.ones((2, 1, 2, 2), dtype=np.float32))
c = relay.nn.conv2d(data,
weight,
padding=(0, 0, 0, 0),
kernel_layout='OIHW')
func = relay.Function([data], c)
mod = tvm.IRModule.from_expr(func)
mod = relay.transform.InferType()(mod)
xg = xf_relay.from_relay(mod, {})
layers = xg.get_layers()
assert len(layers) == 2
assert layers[0].type[0] == 'Input'
assert 'relay_id' in layers[0].attrs
X = layers[1]
assert X.type[0] == 'Convolution'
assert X.shapes == [-1, 2, 3, 3]
np.testing.assert_array_equal(X.data[0],
np.ones((2, 1, 2, 2), dtype=np.float32))
assert 'relay_id' in X.attrs
assert X.attrs['kernel_size'] == [2, 2]
assert X.attrs['strides'] == [1, 1]
assert X.attrs['padding'] == [[0, 0], [0, 0], [0, 0], [0, 0]]
assert X.attrs['channels'] == [1, 2]
assert X.attrs['data_layout'] == 'NCHW'
assert X.attrs['kernel_layout'] == 'OIHW'
assert X.attrs['groups'] == 1
def test_take(self):
data = relay.var("data", relay.TensorType((-1, 3, 224, 224),
"float32"))
indices = relay.var("indices", relay.TensorType([], "int32"))
net = relay.take(data, indices, axis=1)
net = relay.Function(relay.analysis.free_vars(net), net)
mod = tvm.IRModule.from_expr(net)
mod = relay.transform.InferType()(mod)
xgraph = xf_relay.from_relay(mod, {"indices": np.array(0, np.int32)})
layers = xgraph.get_layers()
assert layers[0].type[0] == "Input"
assert layers[1].type[0] == "Constant"
assert layers[1].data == np.array(0, np.int32)
assert layers[2].type[0] == "Take"
assert "relay_id" in layers[2].attrs
assert layers[2].attrs["axis"] == 1
assert layers[2].attrs["mode"] == "clip"
assert layers[2].shapes == [-1, 224, 224]
def test_nn_upsampling(self):
data = relay.var("data", relay.TensorType((-1, 4, 2, 2), "float32"))
net = relay.nn.upsampling(data, scale_h=3, scale_w=2)
net = relay.Function([data], net)
mod = tvm.IRModule.from_expr(net)
mod = relay.transform.InferType()(mod)
params = {}
xgraph = xf_relay.from_relay(mod, params)
layers = xgraph.get_layers()
assert layers[0].type[0] == 'Input'
assert layers[1].type[0] == 'Upsampling2D'
assert 'relay_id' in layers[1].attrs
assert layers[1].shapes == [-1, 4, 6, 4]
assert layers[1].attrs['scale_h'] == 3
assert layers[1].attrs['scale_w'] == 2
assert layers[1].attrs['data_layout'] == 'NCHW'
assert layers[1].attrs['method'] == 'nearest_neighbor'
assert layers[1].attrs['align_corners'] is False
def test_max_pool2d(self):
var = relay.var("var", relay.TensorType((-1, 2, 4, 4), "float32"))
avg_pool = relay.nn.max_pool2d(var,
pool_size=(2, 2),
strides=(2, 2),
padding=(1, 1))
func = relay.Function([var], avg_pool)
mod = tvm.IRModule.from_expr(func)
mod = relay.transform.InferType()(mod)
xg = xf_relay.from_relay(mod, {})
layers = xg.get_layers()
assert len(layers) == 2
assert layers[0].type[0] == "Input"
assert "relay_id" in layers[0].attrs
X = layers[1]
assert X.type[0] == "Pooling"
assert X.bottoms == ["var"]
assert X.shapes == [-1, 2, 3, 3]
assert "relay_id" in X.attrs
assert X.attrs["padding"] == [[0, 0], [0, 0], [1, 1], [1, 1]]
assert X.attrs["insize"] == [4, 4]
assert X.attrs["outsize"] == [3, 3]
assert X.attrs["data_layout"] == "NCHW"
assert X.attrs["strides"] == [2, 2]
assert X.attrs["kernel_size"] == [2, 2]
assert X.attrs["pool_type"] == "Max"
def test_nn_upsampling(self):
data = relay.var("data", relay.TensorType((-1, 4, 2, 2), "float32"))
net = relay.nn.upsampling(data, scale_h=3, scale_w=2)
net = relay.Function([data], net)
mod = tvm.IRModule.from_expr(net)
mod = relay.transform.InferType()(mod)
params = {}
xgraph = xf_relay.from_relay(mod, params)
layers = xgraph.get_layers()
assert layers[0].type[0] == "Input"
assert layers[1].type[0] == "Upsampling2D"
assert "relay_id" in layers[1].attrs
assert layers[1].shapes == [-1, 4, 6, 4]
assert layers[1].attrs["scale_h"] == 3
assert layers[1].attrs["scale_w"] == 2
assert layers[1].attrs["data_layout"] == "NCHW"
assert layers[1].attrs["method"] == "nearest_neighbor"
assert layers[1].attrs["align_corners"] is False
def test_conv2d_transpose(self):
data = relay.var("data", relay.TensorType((-1, 1, 3, 3), "float32"))
weight = relay.var("weight")
simple_net = relay.nn.conv2d_transpose(
data=data,
weight=weight,
kernel_size=(2, 2),
channels=1,
padding=(0, 0),
strides=(2, 2),
data_layout="NCHW",
kernel_layout="IOHW",
)
simple_net = relay.Function(relay.analysis.free_vars(simple_net),
simple_net)
mod, params = testing.create_workload(simple_net)
xgraph = xf_relay.from_relay(mod, params)
layers = xgraph.get_layers()
assert layers[0].type[0] == "Input"
assert layers[0].shapes == [-1, 1, 3, 3]
assert layers[1].type[0] == "Conv2DTranspose"
assert layers[1].shapes == [-1, 1, 6, 6]
assert layers[1].sizes == [36]
assert layers[1].attrs["padding"] == [[0, 0], [0, 0], [0, 0], [0, 0]]
assert layers[1].attrs["strides"] == [2, 2]
assert layers[1].attrs["dilation"] == [1, 1]
def test_simple_network(self):
data = relay.var(
"data",
relay.TensorType((-1, 3, 224, 224), "float32")
)
weight = relay.var("weight")
bn_gamma = relay.var("bn_gamma")
bn_beta = relay.var("bn_beta")
bn_mmean = relay.var("bn_mean")
bn_mvar = relay.var("bn_var")
simple_net = relay.nn.pad(data, ((0, 0), (0, 0), (1, 1), (1, 1)))
simple_net = relay.nn.conv2d(
data=simple_net,
weight=weight,
kernel_size=(3, 3),
channels=16,
padding=(0, 0)
)
simple_net = relay.nn.batch_norm(
simple_net,
bn_gamma,
bn_beta,
bn_mmean,
bn_mvar
)[0]
simple_net = relay.nn.relu(simple_net)
simple_net = relay.op.reduce.mean(simple_net, axis=(2, 3))
simple_net = relay.op.transform.squeeze(simple_net)
dense_weight = relay.var("dense_weight")
dense_bias = relay.var('dense_bias')
simple_net = relay.nn.dense(simple_net, weight=dense_weight, units=10)
simple_net = relay.nn.bias_add(simple_net, dense_bias, axis=1)
simple_net = relay.nn.softmax(simple_net, axis=1)
simple_net = relay.op.transform.reshape(simple_net, newshape=(-1, 10))
simple_net = relay.Function(
relay.analysis.free_vars(simple_net),
simple_net
)
mod, params = testing.create_workload(simple_net)
xgraph = xf_relay.from_relay(mod, params)
layers = xgraph.get_layers()
assert(layers[0].type[0] == 'Input')
assert(layers[1].type[0] == 'Pad')
assert(layers[2].type[0] == 'Convolution')
assert(layers[3].type[0] == 'BatchNorm')
assert(layers[4].type[0] == 'ReLU')
assert(layers[5].type[0] == 'Mean')
assert(layers[6].type[0] == 'Squeeze')
assert(layers[7].type[0] == 'Dense')
assert(layers[8].type[0] == 'BiasAdd')
assert(layers[9].type[0] == 'Softmax')
assert(layers[10].type[0] == 'Reshape')
def test_nn_adaptive_avg_pool2d_3(self):
warnings.filterwarnings("ignore")
data = relay.var("data", relay.TensorType((-1, 6, 6, 4), "float32"))
net = relay.nn.adaptive_avg_pool2d(data,
output_size=(6, 6),
layout="NHWC")
net = relay.Function(relay.analysis.free_vars(net), net)
mod, params = testing.create_workload(net)
xgraph = xf_relay.from_relay(mod, params)
layers = xgraph.get_layers()
assert layers[0].type[0] == "Input"
assert layers[0].shapes.tolist() == [-1, 6, 6, 4]
assert layers[1].type[0] == "Transpose"
assert layers[1].shapes.tolist() == [-1, 4, 6, 6]
assert layers[2].type[0] == "Pooling"
assert layers[2].shapes.tolist() == [-1, 4, 6, 6]
assert layers[2].attrs["padding"] == [[0, 0], [0, 0], [0, 0], [0, 0]]
assert layers[2].attrs["insize"] == [6, 6]
assert layers[2].attrs["outsize"] == [6, 6]
assert layers[2].attrs["data_layout"] == "NCHW"
assert layers[2].attrs["strides"] == [1, 1]
assert layers[2].attrs["kernel_size"] == [1, 1]
assert layers[2].attrs["pool_type"] == "Avg"
def test_concatenate(self):
var1 = relay.var("data1", relay.TensorType((-1, 4, 2, 2), "float32"))
var2 = relay.var("data2", relay.TensorType((-1, 8, 2, 2), "float32"))
c = relay.concatenate([var1, var2], axis=1)
net = relay.Function([var1, var2], c)
mod = tvm.IRModule.from_expr(net)
mod = relay.transform.InferType()(mod)
xg = xf_relay.from_relay(mod, {})
layers = xg.get_layers()
assert len(layers) == 3
assert layers[0].type[0] == 'Input'
assert layers[0].shapes == [-1, 4, 2, 2]
assert 'relay_id' in layers[0].attrs
assert layers[1].type[0] == 'Input'
assert layers[1].shapes == [-1, 8, 2, 2]
assert 'relay_id' in layers[1].attrs
assert layers[2].type[0] == 'Concat'
assert layers[2].shapes == [-1, 12, 2, 2]
assert layers[2].bottoms == ['data1', 'data2']
assert 'relay_id' in layers[2].attrs
assert layers[2].attrs['axis'] == 1
def test_arange(self):
start = relay.expr.const(1.0)
stop = relay.expr.const(5.0)
interval = relay.expr.const(1.5)
a = relay.arange(start, stop, interval)
net = relay.Function([], a)
mod = tvm.IRModule.from_expr(net)
mod = relay.transform.InferType()(mod)
xgraph = xf_relay.from_relay(mod, {})
layers = xgraph.get_layers()
assert len(layers) == 4
assert layers[0].type[0] == "Constant"
assert layers[0].shapes == [1]
assert layers[1].type[0] == "Constant"
assert layers[1].shapes == [1]
assert layers[2].type[0] == "Constant"
assert layers[2].shapes == [1]
assert layers[3].type[0] == "AnyOp"
assert layers[3].shapes == [3]
def test_nn_adaptive_avg_pool2d_3(self):
warnings.filterwarnings("ignore")
data = relay.var("data", relay.TensorType((-1, 6, 6, 4), "float32"))
net = relay.nn.adaptive_avg_pool2d(data,
output_size=(6, 6),
layout='NHWC')
net = relay.Function(relay.analysis.free_vars(net), net)
mod, params = testing.create_workload(net)
xgraph = xf_relay.from_relay(mod, params)
layers = xgraph.get_layers()
assert layers[0].type[0] == 'Input'
assert layers[0].shapes.tolist() == [-1, 6, 6, 4]
assert layers[1].type[0] == 'Transpose'
assert layers[1].shapes.tolist() == [-1, 4, 6, 6]
assert layers[2].type[0] == 'Pooling'
assert layers[2].shapes.tolist() == [-1, 4, 6, 6]
assert layers[2].attrs['padding'] == [[0, 0], [0, 0], [0, 0], [0, 0]]
assert layers[2].attrs['insize'] == [6, 6]
assert layers[2].attrs['outsize'] == [6, 6]
assert layers[2].attrs['data_layout'] == 'NCHW'
assert layers[2].attrs['strides'] == [1, 1]
assert layers[2].attrs['kernel_size'] == [1, 1]
assert layers[2].attrs['pool_type'] == 'Avg'
def test_global_max_pool2d(self):
var = relay.var("var", relay.TensorType((-1, 2, 5, 5), "float32"))
avg_pool = relay.nn.global_max_pool2d(var)
func = relay.Function([var], avg_pool)
mod = tvm.IRModule.from_expr(func)
mod = relay.transform.InferType()(mod)
xg = xf_relay.from_relay(mod, {})
layers = xg.get_layers()
assert len(layers) == 2
assert layers[0].type[0] == 'Input'
assert 'relay_id' in layers[0].attrs
X = layers[1]
assert X.type[0] == 'Pooling'
assert X.bottoms == ['var']
assert X.shapes == [-1, 2, 1, 1]
assert 'relay_id' in X.attrs
assert X.attrs['padding'] == [[0, 0], [0, 0], [0, 0], [0, 0]]
assert X.attrs['insize'] == [5, 5]
assert X.attrs['outsize'] == [1, 1]
assert X.attrs['data_layout'] == 'NCHW'
assert X.attrs['strides'] == [1, 1]
assert X.attrs['kernel_size'] == [5, 5]
assert X.attrs['pool_type'] == 'Max'
def test_yolo_reorg(self):
data = relay.var("data", relay.TensorType((-1, 4, 2, 2), "float32"))
net = relay.vision.yolo_reorg(data, stride=2)
net = relay.Function(relay.analysis.free_vars(net), net)
mod, params = testing.create_workload(net)
xgraph = xf_relay.from_relay(mod, params)
layers = xgraph.get_layers()
assert layers[0].type[0] == 'Input'
assert layers[1].type[0] == 'YoloReorg'
def test_mean(self):
data = relay.var("data", relay.TensorType((-1, 4, 1, 1), "float32"))
m = relay.mean(data, axis=1)
net = relay.Function([data], m)
mod = tvm.IRModule.from_expr(net)
mod = relay.transform.InferType()(mod)
xgraph = xf_relay.from_relay(mod, {})
layers = xgraph.get_layers()
assert layers[0].type[0] == "Input"
assert layers[1].type[0] == "Mean"
assert layers[1].shapes == [-1, 1, 1]
def test_simple_network(self):
data = relay.var(
"data",
relay.TensorType((-1, 1, 4, 4), "float32")
)
weight = relay.var("weight")
# simple_net = relay.nn.pad(data, ((0, 0), (0, 0), (1, 1), (1, 1)))
simple_net = relay.nn.conv2d(
data=data,
weight=weight,
kernel_size=(2, 2),
channels=2,
padding=(0, 0)
)
simple_net = relay.Function(
relay.analysis.free_vars(simple_net),
simple_net
)
mod, params = testing.create_workload(simple_net)
weight = np.reshape(np.array([[[1, 2], [3, 0]], [[1, 1], [0, 1]]],
dtype=np.float32),
(2, 1, 2, 2))
xgraph = xf_relay.from_relay(mod, {'weight': weight})
layers = xgraph.get_layers()
inputs = {
'data': np.reshape(np.array([
[10, 10, 0, 40],
[50, 10, 0, 80],
[30, 50, 10, 0],
[10, 90, 30, 40]]), (1, 1, 4, 4))
}
res = run._run_network_cpu(xgraph, inputs)
# print(res[0])
expected_outpt = np.array([[
[[180., 40., 80.],
[160., 160., 190.],
[160., 340., 100.]],
[[30., 10., 120.],
[110., 20., 80.],
[170., 90., 50.]]
]])
np.testing.assert_array_equal(res[0], expected_outpt)
def test_strided_slice(self):
c = relay.expr.const(np.ones((2, 3, 4), np.float32))
m = relay.strided_slice(c, (0, 0, 1), (2, 3, 4), (1, 1, 1))
net = relay.Function([], m)
mod = tvm.IRModule.from_expr(net)
mod = relay.transform.InferType()(mod)
xgraph = xf_relay.from_relay(mod, {})
layers = xgraph.get_layers()
assert layers[0].type[0] == "Constant"
assert layers[1].type[0] == "StridedSlice"
assert layers[1].shapes == [2, 3, 3]
def test_ones_like(self):
c = relay.expr.const(np.ones((1, 6, 4, 4), np.float32))
net = relay.ones_like(c)
net = relay.Function([], net)
mod = tvm.IRModule.from_expr(net)
mod = relay.transform.InferType()(mod)
xgraph = xf_relay.from_relay(mod, {})
layers = xgraph.get_layers()
assert layers[0].type[0] == "Constant"
assert layers[1].type[0] == "AnyOp"
assert layers[1].shapes == [1, 6, 4, 4]
