Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[Frontend] Prevent tflite frontend from producing int64 shape/parameters #7030

Merged
merged 2 commits into from
Dec 4, 2020
Merged

[Frontend] Prevent tflite frontend from producing int64 shape/parameters #7030

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
68e6df2
[Frontend] Prevent tflite frontend from producing int64 shape and par…
merrymercy Dec 4, 2020
2432962
fix lint
merrymercy Dec 4, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 11 additions & 0 deletions python/tvm/relay/frontend/common.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -601,3 +601,14 @@ def __call__(self, inputs, attrs, *args):
if "tvm_custom" in attrs:
attrs.pop("tvm_custom")
return get_relay_op(self._new_name)(*inputs, **attrs)


def to_int_list(np_array):
"""Convert a np array to a python int list.

Note: This function converts np.int32 to python's int.
If we don't do this conversion, numpy's automatic upcast will make
the shape / parameters be converted to int64 IntImm in relay and
cause problems in relay/TOPI.
"""
return [int(x) for x in np_array]
33 changes: 19 additions & 14 deletions python/tvm/relay/frontend/tflite.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,7 @@
from .. import qnn as _qnn
from ... import nd as _nd
from .common import ExprTable
from .common import infer_shape as _infer_shape
from .common import infer_shape as _infer_shape, to_int_list
from .tflite_flexbuffer import FlexBufferDecoder


Expand Down Expand Up @@ -345,7 +345,7 @@ def get_tensor_value(self, tensor_wrapper):
data = tensor_wrapper.buffer.DataAsNumpy()

if tensor_wrapper.tensor.ShapeLength() != 0:
shape = tensor_wrapper.tensor.ShapeAsNumpy()
shape = to_int_list(tensor_wrapper.tensor.ShapeAsNumpy())
else:
shape = []

Expand Down Expand Up @@ -503,7 +503,7 @@ def convert_reshape(self, op):
op_options = op.BuiltinOptions()
reshape_options = ReshapeOptions()
reshape_options.Init(op_options.Bytes, op_options.Pos)
target_shape = tuple(reshape_options.NewShapeAsNumpy())
target_shape = to_int_list(reshape_options.NewShapeAsNumpy())

in_expr = self.get_expr(input_tensor_idx)

Expand Down Expand Up @@ -1387,7 +1387,7 @@ def convert_gather(self, op):
axis = gather_options.Axis()

# Check the indices are with in bounds.
data_shape = list(input_tensors[0].tensor.ShapeAsNumpy())
data_shape = to_int_list(input_tensors[0].tensor.ShapeAsNumpy())
data_dim = len(data_shape)

axis = data_dim + axis if axis < 0 else axis
Expand Down Expand Up @@ -1505,7 +1505,7 @@ def convert_strided_slice(self, op):
new_axis_mask = options.NewAxisMask()
shrink_axis_mask = options.ShrinkAxisMask()

data_shape = list(input_tensors[0].tensor.ShapeAsNumpy())
data_shape = to_int_list(input_tensors[0].tensor.ShapeAsNumpy())
data_dim = len(data_shape)
stride_dim = len(stride)

Expand Down Expand Up @@ -1757,7 +1757,7 @@ def convert_fully_connected(self, op):
output_tensor_type = output_tensor.tensor.Type()
output_tensor_type_str = self.get_tensor_type_str(output_tensor_type)

weight_tensor_shape = weight_tensor.tensor.ShapeAsNumpy()
weight_tensor_shape = to_int_list(weight_tensor.tensor.ShapeAsNumpy())

# Weight should have only 2 dimensions(TFLite convention)
assert len(weight_tensor_shape) == 2, "Weight should be only 2-dim"
Expand Down Expand Up @@ -1951,15 +1951,17 @@ def convert_conv(self, op, conv_type):
padding = conv_options.Padding()
fused_activation_fn = conv_options.FusedActivationFunction()

_, input_h, input_w, input_c = input_tensor.tensor.ShapeAsNumpy()
_, input_h, input_w, input_c = to_int_list(input_tensor.tensor.ShapeAsNumpy())

if is_depthwise_conv:
# TFLite depthwise convolution kernel layout is:
# 1 KH KW C(input_c * depth_multiplier)
_, kernel_h, kernel_w, in_channels = weight_tensor.tensor.ShapeAsNumpy()
_, kernel_h, kernel_w, in_channels = to_int_list(weight_tensor.tensor.ShapeAsNumpy())
assert in_channels == input_c * depth_multiplier
else:
output_channels, kernel_h, kernel_w, _ = weight_tensor.tensor.ShapeAsNumpy()
output_channels, kernel_h, kernel_w, _ = to_int_list(
weight_tensor.tensor.ShapeAsNumpy()
)

dilated_kernel_h = dilation_h * (kernel_h - 1) + 1
dilated_kernel_w = dilation_w * (kernel_w - 1) + 1
Expand Down Expand Up @@ -2007,6 +2009,7 @@ def convert_conv(self, op, conv_type):
pass
elif padding == Padding.SAME:
pad_top, pad_bottom = get_pad_value(input_h, dilated_kernel_h, stride_h)

pad_left, pad_right = get_pad_value(input_w, dilated_kernel_w, stride_w)
do_pad = not (pad_top == 0 and pad_bottom == 0 and pad_left == 0 and pad_right == 0)
if do_pad:
Expand Down Expand Up @@ -2160,7 +2163,7 @@ def convert_slice(self, op):
size = list(self.get_tensor_value(input_tensors[2]))
# strided_slice(Relay) needs the slice's end indices, not the size
end = size
input_tensor_shape = input_tensor.tensor.ShapeAsNumpy()
input_tensor_shape = to_int_list(input_tensor.tensor.ShapeAsNumpy())
input_tensor_rank = len(input_tensor_shape)
for i in range(input_tensor_rank):
if size[i] == -1:
Expand Down Expand Up @@ -2322,7 +2325,7 @@ def convert_pool2d(self, op, pool_type):

in_expr = self.get_expr(input_tensor_idx)

_, input_h, input_w, _ = input_tensor.tensor.ShapeAsNumpy()
_, input_h, input_w, _ = to_int_list(input_tensor.tensor.ShapeAsNumpy())
if padding == Padding.VALID:
pass
elif padding == Padding.SAME:
Expand Down Expand Up @@ -2701,10 +2704,12 @@ def convert_transpose_conv(self, op):

# Input (data) Tensor. NHWC layout
input_tensor = input_tensors[2]
_, input_h, input_w, input_c = input_tensor.tensor.ShapeAsNumpy()
_, input_h, input_w, input_c = to_int_list(input_tensor.tensor.ShapeAsNumpy())
# Weights tensor. TFLite uses OHWI layout
weights_tensor = input_tensors[1]
out_channels, kernel_h, kernel_w, in_channels = weights_tensor.tensor.ShapeAsNumpy()
out_channels, kernel_h, kernel_w, in_channels = to_int_list(
weights_tensor.tensor.ShapeAsNumpy()
)
assert (
input_c == in_channels
), "Input channel in the filter should match to channel in the input"
Expand Down Expand Up @@ -3120,7 +3125,7 @@ def convert_matrix_diag(self, op):
), "TFLite MATRIX_DIAG requires diagonal and output tensors' \
scale and zero points to be equal"

shape = diagonal.tensor.ShapeAsNumpy()
shape = to_int_list(diagonal.tensor.ShapeAsNumpy())
shape = np.append(shape, shape[-1])
dtype = self.get_tensor_type_str(diagonal.tensor.Type())

Expand Down