You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by GitBox <gi...@apache.org> on 2020/01/29 11:44:06 UTC
[GitHub] [incubator-tvm] siju-samuel opened a new pull request #4788:
[FRONTEND][TFLITE]Gather, StridedSlice op support added
siju-samuel opened a new pull request #4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added
URL: https://github.com/apache/incubator-tvm/pull/4788
Thanks for contributing to TVM! Please refer to guideline https://docs.tvm.ai/contribute/ for useful information and tips. After the pull request is submitted, please request code reviews from [Reviewers](https://github.com/apache/incubator-tvm/blob/master/CONTRIBUTORS.md#reviewers) by @ them in the pull request thread.
@FrozenGene @kevinthesun Could you please help to review this patch. TIA
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
[GitHub] [incubator-tvm] siju-samuel commented on a change in pull request
#4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added
Posted by GitBox <gi...@apache.org>.
siju-samuel commented on a change in pull request #4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added
URL: https://github.com/apache/incubator-tvm/pull/4788#discussion_r379762188
##########
File path: tests/python/frontend/tflite/test_forward.py
##########
@@ -244,6 +244,74 @@ def test_forward_slice():
_test_slice(np.arange(8, dtype=np.int32).reshape((2, 4)), begin=[0, 1], size=[-1, -1])
_test_slice(np.arange(5, dtype=np.int32).reshape((5, )), begin=[4], size=[-1])
+#######################################################################
+# Gather
+# ------
+
+def _test_gather(dshape, indices, axis, dtype):
+ """ One iteration of Gather """
+ data = np.random.uniform(1, 10, size=dshape).astype(dtype)
+ indices = np.asarray(indices).astype('int32')
+
+ with tf.Graph().as_default():
+ in_data = array_ops.placeholder(shape=data.shape, dtype=data.dtype)
+ out = array_ops.gather(in_data, indices, axis=axis)
+ compare_tflite_with_tvm(data, 'Placeholder:0', [in_data], [out])
+
+ #Test quantized input
+ data = np.random.uniform(1, 10, size=dshape).astype(np.uint8)
+ with tf.Graph().as_default():
+ in_data = array_ops.placeholder(shape=data.shape, dtype=data.dtype, name="in_data")
+ out = array_ops.gather(in_data, indices, axis=axis)
+ compare_tflite_with_tvm([data], ['in_data:0'], [in_data], [out], quantized=True)
+
+def test_forward_gather():
+ """ GATHER """
+ _test_gather((4,), [1], 0, 'float32')
+ _test_gather((1, 4), [0], 0, 'int32')
+ _test_gather((4,), [[[1, 0], [0, 1]]], 0, 'float32')
+ _test_gather((2, 2), [[[1, 0], [0, 1]]], 0, 'int32')
+ _test_gather((2, 2), [[[1, 0], [0, 1]]], 1, 'int32')
+ _test_gather((2, 2), [[[1, 0], [0, 1]]], 0, 'float32')
+ _test_gather((3, 3, 3), [[[1, 0]]], 0, 'int32')
+ _test_gather((3, 3, 3), [[[1, 0]]], 2, 'int32')
+ _test_gather((4, 3, 5, 6), [[2, 1, 0, 0]], 0, 'float32')
+
+#######################################################################
+# StridedSlice
+# ------------
+
+def _test_stridedslice(ip_shape, begin, end, stride, dtype,
+ begin_mask=0, end_mask=0, new_axis_mask=0,
+ shrink_axis_mask=0, ellipsis_mask=0):
+ """ One iteration of a Stridedslice """
+ data = np.random.uniform(size=ip_shape).astype(dtype)
+ with tf.Graph().as_default():
+ in_data = tf.placeholder(dtype, ip_shape, name="in_data")
+ out = array_ops.strided_slice(in_data, begin, end, stride,
+ begin_mask=begin_mask,
+ end_mask=end_mask, new_axis_mask=new_axis_mask,
+ shrink_axis_mask=shrink_axis_mask,
+ ellipsis_mask=ellipsis_mask)
+ compare_tflite_with_tvm(data, 'in_data:0', [in_data], [out])
+
+ #Test with quantized inputs
+ data = np.random.uniform(size=ip_shape).astype(np.uint8)
+ with tf.Graph().as_default():
+ in_data = tf.placeholder(dtype, ip_shape, name="in_data")
+ out = array_ops.strided_slice(in_data, begin, end, stride,
+ begin_mask=begin_mask,
+ end_mask=end_mask, new_axis_mask=new_axis_mask,
+ shrink_axis_mask=shrink_axis_mask,
+ ellipsis_mask=ellipsis_mask)
+ compare_tflite_with_tvm([data], ['in_data:0'], [in_data], [out], quantized=True)
Review comment:
Its merged together as per your suggestion. Thanks.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
[GitHub] [incubator-tvm] u99127 commented on a change in pull request #4788:
[FRONTEND][TFLITE]Gather, StridedSlice op support added
Posted by GitBox <gi...@apache.org>.
u99127 commented on a change in pull request #4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added
URL: https://github.com/apache/incubator-tvm/pull/4788#discussion_r376673796
##########
File path: tests/python/frontend/tflite/test_forward.py
##########
@@ -244,6 +244,74 @@ def test_forward_slice():
_test_slice(np.arange(8, dtype=np.int32).reshape((2, 4)), begin=[0, 1], size=[-1, -1])
_test_slice(np.arange(5, dtype=np.int32).reshape((5, )), begin=[4], size=[-1])
+#######################################################################
+# Gather
+# ------
+
+def _test_gather(dshape, indices, axis, dtype):
+ """ One iteration of Gather """
+ data = np.random.uniform(1, 10, size=dshape).astype(dtype)
+ indices = np.asarray(indices).astype('int32')
+
+ with tf.Graph().as_default():
+ in_data = array_ops.placeholder(shape=data.shape, dtype=data.dtype)
+ out = array_ops.gather(in_data, indices, axis=axis)
+ compare_tflite_with_tvm(data, 'Placeholder:0', [in_data], [out])
+
+ #Test quantized input
+ data = np.random.uniform(1, 10, size=dshape).astype(np.uint8)
+ with tf.Graph().as_default():
+ in_data = array_ops.placeholder(shape=data.shape, dtype=data.dtype, name="in_data")
+ out = array_ops.gather(in_data, indices, axis=axis)
+ compare_tflite_with_tvm([data], ['in_data:0'], [in_data], [out], quantized=True)
+
+def test_forward_gather():
+ """ GATHER """
+ _test_gather((4,), [1], 0, 'float32')
+ _test_gather((1, 4), [0], 0, 'int32')
+ _test_gather((4,), [[[1, 0], [0, 1]]], 0, 'float32')
+ _test_gather((2, 2), [[[1, 0], [0, 1]]], 0, 'int32')
+ _test_gather((2, 2), [[[1, 0], [0, 1]]], 1, 'int32')
+ _test_gather((2, 2), [[[1, 0], [0, 1]]], 0, 'float32')
+ _test_gather((3, 3, 3), [[[1, 0]]], 0, 'int32')
+ _test_gather((3, 3, 3), [[[1, 0]]], 2, 'int32')
+ _test_gather((4, 3, 5, 6), [[2, 1, 0, 0]], 0, 'float32')
+
+#######################################################################
+# StridedSlice
+# ------------
+
+def _test_stridedslice(ip_shape, begin, end, stride, dtype,
+ begin_mask=0, end_mask=0, new_axis_mask=0,
+ shrink_axis_mask=0, ellipsis_mask=0):
+ """ One iteration of a Stridedslice """
+ data = np.random.uniform(size=ip_shape).astype(dtype)
+ with tf.Graph().as_default():
+ in_data = tf.placeholder(dtype, ip_shape, name="in_data")
+ out = array_ops.strided_slice(in_data, begin, end, stride,
+ begin_mask=begin_mask,
+ end_mask=end_mask, new_axis_mask=new_axis_mask,
+ shrink_axis_mask=shrink_axis_mask,
+ ellipsis_mask=ellipsis_mask)
+ compare_tflite_with_tvm(data, 'in_data:0', [in_data], [out])
+
+ #Test with quantized inputs
+ data = np.random.uniform(size=ip_shape).astype(np.uint8)
+ with tf.Graph().as_default():
+ in_data = tf.placeholder(dtype, ip_shape, name="in_data")
+ out = array_ops.strided_slice(in_data, begin, end, stride,
+ begin_mask=begin_mask,
+ end_mask=end_mask, new_axis_mask=new_axis_mask,
+ shrink_axis_mask=shrink_axis_mask,
+ ellipsis_mask=ellipsis_mask)
+ compare_tflite_with_tvm([data], ['in_data:0'], [in_data], [out], quantized=True)
+
+def test_forward_stridedslice():
+ '''test StridedSlice'''
Review comment:
@wyc-ruiker - might help to specify what situations you see missing to help with actionable feedback ?
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
[GitHub] [incubator-tvm] wyc-ruiker commented on a change in pull request
#4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added
Posted by GitBox <gi...@apache.org>.
wyc-ruiker commented on a change in pull request #4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added
URL: https://github.com/apache/incubator-tvm/pull/4788#discussion_r374734446
##########
File path: python/tvm/relay/frontend/tflite.py
##########
@@ -792,6 +794,147 @@ def convert_not_equal(self, op):
'TFlite quantized NOT_EQUAL operator is not supported yet.')
return self._convert_elemwise(_op.not_equal, op)
+ def convert_gather(self, op):
+ """Method to Convert TFLite GATHER operator"""
+ try:
+ from tflite.BuiltinOptions import BuiltinOptions
+ from tflite.GatherOptions import GatherOptions
+ from tflite.TensorType import TensorType
+ except ImportError:
+ raise ImportError("The tflite package must be installed")
+
+ input_tensors = self.get_input_tensors(op)
+ data = self.get_expr(input_tensors[0].tensor_idx)
+
+ indices = input_tensors[1]
+ indices_type = indices.tensor.Type()
+ assert indices_type in (TensorType.INT32, TensorType.INT64)
+ indices_type_str = self.get_tensor_type_str(indices_type)
+ indices = self.exp_tab.new_const(self.get_tensor_value(indices),
+ dtype=indices_type_str)
+
+ assert op.BuiltinOptionsType() == BuiltinOptions.GatherOptions
+ op_options = op.BuiltinOptions()
+ gather_options = GatherOptions()
+ gather_options.Init(op_options.Bytes, op_options.Pos)
+ axis = gather_options.Axis()
+
+ out = _op.take(data, indices, axis=axis)
+ return out
+
+ def convert_strided_slice(self, op):
+ """Method to Convert TFLite STRIDED_SLICE operator"""
+ try:
+ from tflite.BuiltinOptions import BuiltinOptions
+ from tflite.StridedSliceOptions import StridedSliceOptions
+ except ImportError:
+ raise ImportError("The tflite package must be installed")
+
+ input_tensors = self.get_input_tensors(op)
Review comment:
We also need an assert here.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
[GitHub] [incubator-tvm] siju-samuel commented on a change in pull request
#4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added
Posted by GitBox <gi...@apache.org>.
siju-samuel commented on a change in pull request #4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added
URL: https://github.com/apache/incubator-tvm/pull/4788#discussion_r379762683
##########
File path: python/tvm/relay/frontend/tflite.py
##########
@@ -792,6 +794,147 @@ def convert_not_equal(self, op):
'TFlite quantized NOT_EQUAL operator is not supported yet.')
return self._convert_elemwise(_op.not_equal, op)
+ def convert_gather(self, op):
+ """Method to Convert TFLite GATHER operator"""
+ try:
+ from tflite.BuiltinOptions import BuiltinOptions
+ from tflite.GatherOptions import GatherOptions
+ from tflite.TensorType import TensorType
+ except ImportError:
+ raise ImportError("The tflite package must be installed")
+
+ input_tensors = self.get_input_tensors(op)
+ data = self.get_expr(input_tensors[0].tensor_idx)
+
+ indices = input_tensors[1]
+ indices_type = indices.tensor.Type()
+ assert indices_type in (TensorType.INT32, TensorType.INT64)
+ indices_type_str = self.get_tensor_type_str(indices_type)
+ indices = self.exp_tab.new_const(self.get_tensor_value(indices),
+ dtype=indices_type_str)
+
+ assert op.BuiltinOptionsType() == BuiltinOptions.GatherOptions
+ op_options = op.BuiltinOptions()
+ gather_options = GatherOptions()
+ gather_options.Init(op_options.Bytes, op_options.Pos)
+ axis = gather_options.Axis()
+
+ out = _op.take(data, indices, axis=axis)
+ return out
+
+ def convert_strided_slice(self, op):
+ """Method to Convert TFLite STRIDED_SLICE operator"""
+ try:
+ from tflite.BuiltinOptions import BuiltinOptions
+ from tflite.StridedSliceOptions import StridedSliceOptions
+ except ImportError:
+ raise ImportError("The tflite package must be installed")
+
+ input_tensors = self.get_input_tensors(op)
Review comment:
Added the assert as per your suggestion
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
[GitHub] [incubator-tvm] wyc-ruiker commented on a change in pull request
#4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added
Posted by GitBox <gi...@apache.org>.
wyc-ruiker commented on a change in pull request #4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added
URL: https://github.com/apache/incubator-tvm/pull/4788#discussion_r374733608
##########
File path: python/tvm/relay/frontend/tflite.py
##########
@@ -792,6 +794,147 @@ def convert_not_equal(self, op):
'TFlite quantized NOT_EQUAL operator is not supported yet.')
return self._convert_elemwise(_op.not_equal, op)
+ def convert_gather(self, op):
+ """Method to Convert TFLite GATHER operator"""
+ try:
+ from tflite.BuiltinOptions import BuiltinOptions
+ from tflite.GatherOptions import GatherOptions
+ from tflite.TensorType import TensorType
+ except ImportError:
+ raise ImportError("The tflite package must be installed")
+
+ input_tensors = self.get_input_tensors(op)
Review comment:
We need an assert here like `assert len(input_tensors) == 2, "input tensors length should be 2"`
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
[GitHub] [incubator-tvm] siju-samuel commented on a change in pull request
#4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added
Posted by GitBox <gi...@apache.org>.
siju-samuel commented on a change in pull request #4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added
URL: https://github.com/apache/incubator-tvm/pull/4788#discussion_r379762709
##########
File path: tests/python/frontend/tflite/test_forward.py
##########
@@ -244,6 +244,74 @@ def test_forward_slice():
_test_slice(np.arange(8, dtype=np.int32).reshape((2, 4)), begin=[0, 1], size=[-1, -1])
_test_slice(np.arange(5, dtype=np.int32).reshape((5, )), begin=[4], size=[-1])
+#######################################################################
+# Gather
+# ------
+
+def _test_gather(dshape, indices, axis, dtype):
+ """ One iteration of Gather """
+ data = np.random.uniform(1, 10, size=dshape).astype(dtype)
+ indices = np.asarray(indices).astype('int32')
+
+ with tf.Graph().as_default():
+ in_data = array_ops.placeholder(shape=data.shape, dtype=data.dtype)
+ out = array_ops.gather(in_data, indices, axis=axis)
+ compare_tflite_with_tvm(data, 'Placeholder:0', [in_data], [out])
+
+ #Test quantized input
+ data = np.random.uniform(1, 10, size=dshape).astype(np.uint8)
+ with tf.Graph().as_default():
+ in_data = array_ops.placeholder(shape=data.shape, dtype=data.dtype, name="in_data")
+ out = array_ops.gather(in_data, indices, axis=axis)
+ compare_tflite_with_tvm([data], ['in_data:0'], [in_data], [out], quantized=True)
+
+def test_forward_gather():
+ """ GATHER """
+ _test_gather((4,), [1], 0, 'float32')
+ _test_gather((1, 4), [0], 0, 'int32')
+ _test_gather((4,), [[[1, 0], [0, 1]]], 0, 'float32')
+ _test_gather((2, 2), [[[1, 0], [0, 1]]], 0, 'int32')
+ _test_gather((2, 2), [[[1, 0], [0, 1]]], 1, 'int32')
+ _test_gather((2, 2), [[[1, 0], [0, 1]]], 0, 'float32')
+ _test_gather((3, 3, 3), [[[1, 0]]], 0, 'int32')
+ _test_gather((3, 3, 3), [[[1, 0]]], 2, 'int32')
+ _test_gather((4, 3, 5, 6), [[2, 1, 0, 0]], 0, 'float32')
+
+#######################################################################
+# StridedSlice
+# ------------
+
+def _test_stridedslice(ip_shape, begin, end, stride, dtype,
+ begin_mask=0, end_mask=0, new_axis_mask=0,
+ shrink_axis_mask=0, ellipsis_mask=0):
+ """ One iteration of a Stridedslice """
+ data = np.random.uniform(size=ip_shape).astype(dtype)
+ with tf.Graph().as_default():
+ in_data = tf.placeholder(dtype, ip_shape, name="in_data")
+ out = array_ops.strided_slice(in_data, begin, end, stride,
+ begin_mask=begin_mask,
+ end_mask=end_mask, new_axis_mask=new_axis_mask,
+ shrink_axis_mask=shrink_axis_mask,
+ ellipsis_mask=ellipsis_mask)
+ compare_tflite_with_tvm(data, 'in_data:0', [in_data], [out])
+
+ #Test with quantized inputs
+ data = np.random.uniform(size=ip_shape).astype(np.uint8)
+ with tf.Graph().as_default():
+ in_data = tf.placeholder(dtype, ip_shape, name="in_data")
+ out = array_ops.strided_slice(in_data, begin, end, stride,
+ begin_mask=begin_mask,
+ end_mask=end_mask, new_axis_mask=new_axis_mask,
+ shrink_axis_mask=shrink_axis_mask,
+ ellipsis_mask=ellipsis_mask)
+ compare_tflite_with_tvm([data], ['in_data:0'], [in_data], [out], quantized=True)
+
+def test_forward_stridedslice():
+ '''test StridedSlice'''
Review comment:
Even though tf2.0 supports begin_mask, end_mask, ellipsis_mask, new_axis_mask and shrink_axis_mask, tflite doesn't support these and expect these values to be zero. So we donot need to import all cases from tensorflow testcases.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
[GitHub] [incubator-tvm] tqchen commented on issue #4788:
[FRONTEND][TFLITE]Gather, StridedSlice op support added
Posted by GitBox <gi...@apache.org>.
tqchen commented on issue #4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added
URL: https://github.com/apache/incubator-tvm/pull/4788#issuecomment-591701888
ping @siju-samuel please followup on the review comments @FrozenGene @wyc-ruiker please https://docs.tvm.ai/contribute/code_review.html#approve-and-request-changes-explicitly
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
[GitHub] [incubator-tvm] u99127 commented on a change in pull request #4788:
[FRONTEND][TFLITE]Gather, StridedSlice op support added
Posted by GitBox <gi...@apache.org>.
u99127 commented on a change in pull request #4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added
URL: https://github.com/apache/incubator-tvm/pull/4788#discussion_r374499522
##########
File path: tests/python/frontend/tflite/test_forward.py
##########
@@ -244,6 +244,74 @@ def test_forward_slice():
_test_slice(np.arange(8, dtype=np.int32).reshape((2, 4)), begin=[0, 1], size=[-1, -1])
_test_slice(np.arange(5, dtype=np.int32).reshape((5, )), begin=[4], size=[-1])
+#######################################################################
+# Gather
+# ------
+
+def _test_gather(dshape, indices, axis, dtype):
+ """ One iteration of Gather """
+ data = np.random.uniform(1, 10, size=dshape).astype(dtype)
+ indices = np.asarray(indices).astype('int32')
+
+ with tf.Graph().as_default():
+ in_data = array_ops.placeholder(shape=data.shape, dtype=data.dtype)
+ out = array_ops.gather(in_data, indices, axis=axis)
+ compare_tflite_with_tvm(data, 'Placeholder:0', [in_data], [out])
+
+ #Test quantized input
+ data = np.random.uniform(1, 10, size=dshape).astype(np.uint8)
+ with tf.Graph().as_default():
+ in_data = array_ops.placeholder(shape=data.shape, dtype=data.dtype, name="in_data")
+ out = array_ops.gather(in_data, indices, axis=axis)
+ compare_tflite_with_tvm([data], ['in_data:0'], [in_data], [out], quantized=True)
Review comment:
Can we remove this by calling _test_gather with np.uint8 instead of duplicating logic ?
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
[GitHub] [incubator-tvm] FrozenGene commented on issue #4788:
[FRONTEND][TFLITE]Gather, StridedSlice op support added
Posted by GitBox <gi...@apache.org>.
FrozenGene commented on issue #4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added
URL: https://github.com/apache/incubator-tvm/pull/4788#issuecomment-598040228
@siju-samuel please rebase
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
[GitHub] [incubator-tvm] siju-samuel commented on a change in pull request
#4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added
Posted by GitBox <gi...@apache.org>.
siju-samuel commented on a change in pull request #4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added
URL: https://github.com/apache/incubator-tvm/pull/4788#discussion_r379762146
##########
File path: tests/python/frontend/tflite/test_forward.py
##########
@@ -244,6 +244,74 @@ def test_forward_slice():
_test_slice(np.arange(8, dtype=np.int32).reshape((2, 4)), begin=[0, 1], size=[-1, -1])
_test_slice(np.arange(5, dtype=np.int32).reshape((5, )), begin=[4], size=[-1])
+#######################################################################
+# Gather
+# ------
+
+def _test_gather(dshape, indices, axis, dtype):
+ """ One iteration of Gather """
+ data = np.random.uniform(1, 10, size=dshape).astype(dtype)
+ indices = np.asarray(indices).astype('int32')
+
+ with tf.Graph().as_default():
+ in_data = array_ops.placeholder(shape=data.shape, dtype=data.dtype)
+ out = array_ops.gather(in_data, indices, axis=axis)
+ compare_tflite_with_tvm(data, 'Placeholder:0', [in_data], [out])
+
+ #Test quantized input
+ data = np.random.uniform(1, 10, size=dshape).astype(np.uint8)
+ with tf.Graph().as_default():
+ in_data = array_ops.placeholder(shape=data.shape, dtype=data.dtype, name="in_data")
+ out = array_ops.gather(in_data, indices, axis=axis)
+ compare_tflite_with_tvm([data], ['in_data:0'], [in_data], [out], quantized=True)
+
+def test_forward_gather():
+ """ GATHER """
+ _test_gather((4,), [1], 0, 'float32')
+ _test_gather((1, 4), [0], 0, 'int32')
+ _test_gather((4,), [[[1, 0], [0, 1]]], 0, 'float32')
+ _test_gather((2, 2), [[[1, 0], [0, 1]]], 0, 'int32')
+ _test_gather((2, 2), [[[1, 0], [0, 1]]], 1, 'int32')
+ _test_gather((2, 2), [[[1, 0], [0, 1]]], 0, 'float32')
+ _test_gather((3, 3, 3), [[[1, 0]]], 0, 'int32')
+ _test_gather((3, 3, 3), [[[1, 0]]], 2, 'int32')
+ _test_gather((4, 3, 5, 6), [[2, 1, 0, 0]], 0, 'float32')
Review comment:
Tflite has seperate implementation for oob indices, for tflite cpu, the return error and gpu they return 0 for the oob indices. but in my testing, oob cases are not predictable.
TVM doesnt support returning zero for 'take' oob indices.
So while parsing, im checking whether the indices are oob and throwing exception currently.
Testcases are added for the above scenario.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
[GitHub] [incubator-tvm] u99127 commented on a change in pull request #4788:
[FRONTEND][TFLITE]Gather, StridedSlice op support added
Posted by GitBox <gi...@apache.org>.
u99127 commented on a change in pull request #4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added
URL: https://github.com/apache/incubator-tvm/pull/4788#discussion_r381990653
##########
File path: python/tvm/relay/frontend/tflite.py
##########
@@ -852,6 +855,193 @@ def convert_logical_or(self, op):
"""Convert tflite LOGICAL_OR"""
return self._convert_logical_binary(_op.logical_or, op)
+ def convert_gather(self, op):
+ """Method to Convert TFLite GATHER operator"""
+ try:
+ from tflite.BuiltinOptions import BuiltinOptions
+ from tflite.GatherOptions import GatherOptions
+ from tflite.TensorType import TensorType
+ except ImportError:
+ raise ImportError("The tflite package must be installed")
+
+ input_tensors = self.get_input_tensors(op)
+ assert len(input_tensors) == 2, "input tensors length should be 2"
+
+ data = self.get_expr(input_tensors[0].tensor_idx)
+
+ indices = input_tensors[1]
+ indices_type = indices.tensor.Type()
+ assert indices_type in (TensorType.INT32, TensorType.INT64)
+ indices_type_str = self.get_tensor_type_str(indices_type)
+ indices = self.exp_tab.new_const(self.get_tensor_value(indices),
+ dtype=indices_type_str)
+
+ assert op.BuiltinOptionsType() == BuiltinOptions.GatherOptions
+ op_options = op.BuiltinOptions()
+ gather_options = GatherOptions()
+ gather_options.Init(op_options.Bytes, op_options.Pos)
+ axis = gather_options.Axis()
+
+ # Check the indices are oob, tflite is unpredictable in case of oob.
Review comment:
Maybe improve comment to :
Check that the indices are within bounds ?
Is the tflite specification clear that out of bounds indices results in unpredictable behaviour ?
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
[GitHub] [incubator-tvm] siju-samuel commented on a change in pull request
#4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added
Posted by GitBox <gi...@apache.org>.
siju-samuel commented on a change in pull request #4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added
URL: https://github.com/apache/incubator-tvm/pull/4788#discussion_r379762580
##########
File path: python/tvm/relay/frontend/tflite.py
##########
@@ -792,6 +794,147 @@ def convert_not_equal(self, op):
'TFlite quantized NOT_EQUAL operator is not supported yet.')
return self._convert_elemwise(_op.not_equal, op)
+ def convert_gather(self, op):
+ """Method to Convert TFLite GATHER operator"""
+ try:
+ from tflite.BuiltinOptions import BuiltinOptions
+ from tflite.GatherOptions import GatherOptions
+ from tflite.TensorType import TensorType
+ except ImportError:
+ raise ImportError("The tflite package must be installed")
+
+ input_tensors = self.get_input_tensors(op)
Review comment:
Added the assert for checking length of input tensors
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
[GitHub] [incubator-tvm] siju-samuel commented on a change in pull request
#4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added
Posted by GitBox <gi...@apache.org>.
siju-samuel commented on a change in pull request #4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added
URL: https://github.com/apache/incubator-tvm/pull/4788#discussion_r382052919
##########
File path: python/tvm/relay/frontend/tflite.py
##########
@@ -852,6 +855,193 @@ def convert_logical_or(self, op):
"""Convert tflite LOGICAL_OR"""
return self._convert_logical_binary(_op.logical_or, op)
+ def convert_gather(self, op):
+ """Method to Convert TFLite GATHER operator"""
+ try:
+ from tflite.BuiltinOptions import BuiltinOptions
+ from tflite.GatherOptions import GatherOptions
+ from tflite.TensorType import TensorType
+ except ImportError:
+ raise ImportError("The tflite package must be installed")
+
+ input_tensors = self.get_input_tensors(op)
+ assert len(input_tensors) == 2, "input tensors length should be 2"
+
+ data = self.get_expr(input_tensors[0].tensor_idx)
+
+ indices = input_tensors[1]
+ indices_type = indices.tensor.Type()
+ assert indices_type in (TensorType.INT32, TensorType.INT64)
+ indices_type_str = self.get_tensor_type_str(indices_type)
+ indices = self.exp_tab.new_const(self.get_tensor_value(indices),
+ dtype=indices_type_str)
+
+ assert op.BuiltinOptionsType() == BuiltinOptions.GatherOptions
+ op_options = op.BuiltinOptions()
+ gather_options = GatherOptions()
+ gather_options.Init(op_options.Bytes, op_options.Pos)
+ axis = gather_options.Axis()
+
+ # Check the indices are oob, tflite is unpredictable in case of oob.
Review comment:
According to [tf latest code](https://github.com/tensorflow/tensorflow/blob/e5bf8de410005de06a7ff5393fafdf832ef1d4ad/tensorflow/python/ops/array_ops.py#L4069), if indices are not within bounds, they will return error for CPU and for GPU they will return zero.
With Tensorflow, i was getting zero for GPU. For validation using _tflite_, i was using tf 1.14 version and i was getting random numbers in places of oob indices.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
[GitHub] [incubator-tvm] wyc-ruiker commented on a change in pull request
#4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added
Posted by GitBox <gi...@apache.org>.
wyc-ruiker commented on a change in pull request #4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added
URL: https://github.com/apache/incubator-tvm/pull/4788#discussion_r381906316
##########
File path: tests/python/frontend/tflite/test_forward.py
##########
@@ -267,6 +267,79 @@ def test_forward_slice():
_test_slice(np.arange(8, dtype=np.int32).reshape((2, 4)), begin=[0, 1], size=[-1, -1])
_test_slice(np.arange(5, dtype=np.int32).reshape((5, )), begin=[4], size=[-1])
+#######################################################################
+# Gather
+# ------
+
+def _test_gather(dshape, indices, axis, dtype, quantized=False, oob=False):
+ """ One iteration of Gather """
+ indices = np.asarray(indices).astype('int32')
+ data = np.random.uniform(1, 10, size=dshape)
+ data = data.astype(np.uint8) if quantized else data.astype(dtype)
+ with tf.Graph().as_default():
+ in_data = array_ops.placeholder(shape=data.shape, dtype=data.dtype, name="in_data")
+ if axis:
+ out = array_ops.gather(in_data, indices, axis=axis)
+ else:
+ out = array_ops.gather(in_data, indices) #tflite conversion fails for None axis
+ input_range = {'in_data': (-100, 100)} if quantized else None
+ try:
+ compare_tflite_with_tvm([data], ['in_data:0'], [in_data], [out],
+ quantized=quantized, input_range=input_range)
+ except ValueError as e:
+ if not oob:
Review comment:
What does `oob` mean？
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
[GitHub] [incubator-tvm] siju-samuel commented on a change in pull request
#4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added
Posted by GitBox <gi...@apache.org>.
siju-samuel commented on a change in pull request #4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added
URL: https://github.com/apache/incubator-tvm/pull/4788#discussion_r381945909
##########
File path: tests/python/frontend/tflite/test_forward.py
##########
@@ -267,6 +267,79 @@ def test_forward_slice():
_test_slice(np.arange(8, dtype=np.int32).reshape((2, 4)), begin=[0, 1], size=[-1, -1])
_test_slice(np.arange(5, dtype=np.int32).reshape((5, )), begin=[4], size=[-1])
+#######################################################################
+# Gather
+# ------
+
+def _test_gather(dshape, indices, axis, dtype, quantized=False, oob=False):
+ """ One iteration of Gather """
+ indices = np.asarray(indices).astype('int32')
+ data = np.random.uniform(1, 10, size=dshape)
+ data = data.astype(np.uint8) if quantized else data.astype(dtype)
+ with tf.Graph().as_default():
+ in_data = array_ops.placeholder(shape=data.shape, dtype=data.dtype, name="in_data")
+ if axis:
+ out = array_ops.gather(in_data, indices, axis=axis)
+ else:
+ out = array_ops.gather(in_data, indices) #tflite conversion fails for None axis
+ input_range = {'in_data': (-100, 100)} if quantized else None
+ try:
+ compare_tflite_with_tvm([data], ['in_data:0'], [in_data], [out],
+ quantized=quantized, input_range=input_range)
+ except ValueError as e:
+ if not oob:
Review comment:
out of bounds
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
[GitHub] [incubator-tvm] siju-samuel commented on issue #4788:
[FRONTEND][TFLITE]Gather, StridedSlice op support added
Posted by GitBox <gi...@apache.org>.
siju-samuel commented on issue #4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added
URL: https://github.com/apache/incubator-tvm/pull/4788#issuecomment-588621902
@u99127 @FrozenGene @wyc-ruiker Thanks for the review. Could you please recheck once again.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
[GitHub] [incubator-tvm] u99127 commented on a change in pull request #4788:
[FRONTEND][TFLITE]Gather, StridedSlice op support added
Posted by GitBox <gi...@apache.org>.
u99127 commented on a change in pull request #4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added
URL: https://github.com/apache/incubator-tvm/pull/4788#discussion_r374500086
##########
File path: python/tvm/relay/frontend/tflite.py
##########
@@ -792,6 +794,147 @@ def convert_not_equal(self, op):
'TFlite quantized NOT_EQUAL operator is not supported yet.')
return self._convert_elemwise(_op.not_equal, op)
+ def convert_gather(self, op):
+ """Method to Convert TFLite GATHER operator"""
+ try:
+ from tflite.BuiltinOptions import BuiltinOptions
+ from tflite.GatherOptions import GatherOptions
+ from tflite.TensorType import TensorType
+ except ImportError:
+ raise ImportError("The tflite package must be installed")
+
+ input_tensors = self.get_input_tensors(op)
+ data = self.get_expr(input_tensors[0].tensor_idx)
+
+ indices = input_tensors[1]
+ indices_type = indices.tensor.Type()
+ assert indices_type in (TensorType.INT32, TensorType.INT64)
+ indices_type_str = self.get_tensor_type_str(indices_type)
+ indices = self.exp_tab.new_const(self.get_tensor_value(indices),
+ dtype=indices_type_str)
+
+ assert op.BuiltinOptionsType() == BuiltinOptions.GatherOptions
+ op_options = op.BuiltinOptions()
+ gather_options = GatherOptions()
+ gather_options.Init(op_options.Bytes, op_options.Pos)
+ axis = gather_options.Axis()
+
+ out = _op.take(data, indices, axis=axis)
+ return out
+
Review comment:
A comment here explaining the lowering from the tflite operator to the relay IR seems appropriate as the code is non-obvious especially as it appears tflite.strided_slice is not identical to relay.op.strided_slice and a final reshape is needed.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
[GitHub] [incubator-tvm] u99127 commented on a change in pull request #4788:
[FRONTEND][TFLITE]Gather, StridedSlice op support added
Posted by GitBox <gi...@apache.org>.
u99127 commented on a change in pull request #4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added
URL: https://github.com/apache/incubator-tvm/pull/4788#discussion_r374498740
##########
File path: tests/python/frontend/tflite/test_forward.py
##########
@@ -244,6 +244,74 @@ def test_forward_slice():
_test_slice(np.arange(8, dtype=np.int32).reshape((2, 4)), begin=[0, 1], size=[-1, -1])
_test_slice(np.arange(5, dtype=np.int32).reshape((5, )), begin=[4], size=[-1])
+#######################################################################
+# Gather
+# ------
+
+def _test_gather(dshape, indices, axis, dtype):
+ """ One iteration of Gather """
+ data = np.random.uniform(1, 10, size=dshape).astype(dtype)
+ indices = np.asarray(indices).astype('int32')
+
+ with tf.Graph().as_default():
+ in_data = array_ops.placeholder(shape=data.shape, dtype=data.dtype)
+ out = array_ops.gather(in_data, indices, axis=axis)
+ compare_tflite_with_tvm(data, 'Placeholder:0', [in_data], [out])
+
+ #Test quantized input
+ data = np.random.uniform(1, 10, size=dshape).astype(np.uint8)
+ with tf.Graph().as_default():
+ in_data = array_ops.placeholder(shape=data.shape, dtype=data.dtype, name="in_data")
+ out = array_ops.gather(in_data, indices, axis=axis)
+ compare_tflite_with_tvm([data], ['in_data:0'], [in_data], [out], quantized=True)
+
+def test_forward_gather():
+ """ GATHER """
+ _test_gather((4,), [1], 0, 'float32')
+ _test_gather((1, 4), [0], 0, 'int32')
+ _test_gather((4,), [[[1, 0], [0, 1]]], 0, 'float32')
+ _test_gather((2, 2), [[[1, 0], [0, 1]]], 0, 'int32')
+ _test_gather((2, 2), [[[1, 0], [0, 1]]], 1, 'int32')
+ _test_gather((2, 2), [[[1, 0], [0, 1]]], 0, 'float32')
+ _test_gather((3, 3, 3), [[[1, 0]]], 0, 'int32')
+ _test_gather((3, 3, 3), [[[1, 0]]], 2, 'int32')
+ _test_gather((4, 3, 5, 6), [[2, 1, 0, 0]], 0, 'float32')
+
+#######################################################################
+# StridedSlice
+# ------------
+
+def _test_stridedslice(ip_shape, begin, end, stride, dtype,
+ begin_mask=0, end_mask=0, new_axis_mask=0,
+ shrink_axis_mask=0, ellipsis_mask=0):
+ """ One iteration of a Stridedslice """
+ data = np.random.uniform(size=ip_shape).astype(dtype)
+ with tf.Graph().as_default():
+ in_data = tf.placeholder(dtype, ip_shape, name="in_data")
+ out = array_ops.strided_slice(in_data, begin, end, stride,
+ begin_mask=begin_mask,
+ end_mask=end_mask, new_axis_mask=new_axis_mask,
+ shrink_axis_mask=shrink_axis_mask,
+ ellipsis_mask=ellipsis_mask)
+ compare_tflite_with_tvm(data, 'in_data:0', [in_data], [out])
+
+ #Test with quantized inputs
+ data = np.random.uniform(size=ip_shape).astype(np.uint8)
+ with tf.Graph().as_default():
+ in_data = tf.placeholder(dtype, ip_shape, name="in_data")
+ out = array_ops.strided_slice(in_data, begin, end, stride,
+ begin_mask=begin_mask,
+ end_mask=end_mask, new_axis_mask=new_axis_mask,
+ shrink_axis_mask=shrink_axis_mask,
+ ellipsis_mask=ellipsis_mask)
+ compare_tflite_with_tvm([data], ['in_data:0'], [in_data], [out], quantized=True)
Review comment:
Can we instead change the caller to call _test_stridedslice with a uint8 data type and avoid duplication of code ? If the data type can't be passed, can the data be created in the caller with an appropriate type and passed in.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
[GitHub] [incubator-tvm] FrozenGene commented on issue #4788:
[FRONTEND][TFLITE]Gather, StridedSlice op support added
Posted by GitBox <gi...@apache.org>.
FrozenGene commented on issue #4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added
URL: https://github.com/apache/incubator-tvm/pull/4788#issuecomment-604521317
@siju-samuel please rebase so that i can handle it.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
[GitHub] [incubator-tvm] siju-samuel commented on issue #4788:
[FRONTEND][TFLITE]Gather, StridedSlice op support added
Posted by GitBox <gi...@apache.org>.
siju-samuel commented on issue #4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added
URL: https://github.com/apache/incubator-tvm/pull/4788#issuecomment-581737945
@FrozenGene @u99127 Thanks for the review and could you please review again.
I have updated as per your review comments.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
[GitHub] [incubator-tvm] siju-samuel commented on a change in pull request
#4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added
Posted by GitBox <gi...@apache.org>.
siju-samuel commented on a change in pull request #4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added
URL: https://github.com/apache/incubator-tvm/pull/4788#discussion_r374469548
##########
File path: tests/python/frontend/tflite/test_forward.py
##########
@@ -244,6 +244,57 @@ def test_forward_slice():
_test_slice(np.arange(8, dtype=np.int32).reshape((2, 4)), begin=[0, 1], size=[-1, -1])
_test_slice(np.arange(5, dtype=np.int32).reshape((5, )), begin=[4], size=[-1])
+#######################################################################
+# Gather
+# ------
+
+def _test_gather(dshape, indices, axis, dtype):
+ """ One iteration of Gather """
+ data = np.random.uniform(1, 10, size=dshape).astype(dtype)
+ indices = np.asarray(indices).astype('int32')
+
+ with tf.Graph().as_default():
+ in_data = array_ops.placeholder(shape=data.shape, dtype=data.dtype)
+ out = array_ops.gather(in_data, indices, axis=axis)
+ compare_tflite_with_tvm(data, 'Placeholder:0', [in_data], [out])
+
+def test_forward_gather():
Review comment:
Since this is a tensor manipulation op, there is no change in the processing. I have added testcases for quantized input data also.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
[GitHub] [incubator-tvm] FrozenGene commented on a change in pull request
#4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added
Posted by GitBox <gi...@apache.org>.
FrozenGene commented on a change in pull request #4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added
URL: https://github.com/apache/incubator-tvm/pull/4788#discussion_r372740391
##########
File path: tests/python/frontend/tflite/test_forward.py
##########
@@ -244,6 +244,57 @@ def test_forward_slice():
_test_slice(np.arange(8, dtype=np.int32).reshape((2, 4)), begin=[0, 1], size=[-1, -1])
_test_slice(np.arange(5, dtype=np.int32).reshape((5, )), begin=[4], size=[-1])
+#######################################################################
+# Gather
+# ------
+
+def _test_gather(dshape, indices, axis, dtype):
+ """ One iteration of Gather """
+ data = np.random.uniform(1, 10, size=dshape).astype(dtype)
+ indices = np.asarray(indices).astype('int32')
+
+ with tf.Graph().as_default():
+ in_data = array_ops.placeholder(shape=data.shape, dtype=data.dtype)
+ out = array_ops.gather(in_data, indices, axis=axis)
+ compare_tflite_with_tvm(data, 'Placeholder:0', [in_data], [out])
+
+def test_forward_gather():
Review comment:
What happened when the input data is quantized?
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
[GitHub] [incubator-tvm] u99127 commented on a change in pull request #4788:
[FRONTEND][TFLITE]Gather, StridedSlice op support added
Posted by GitBox <gi...@apache.org>.
u99127 commented on a change in pull request #4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added
URL: https://github.com/apache/incubator-tvm/pull/4788#discussion_r372389879
##########
File path: python/tvm/relay/frontend/tflite.py
##########
@@ -747,6 +749,158 @@ def convert_squared_difference(self, op):
out = _op.power(difference, relay.const(2, exp_type))
return out
+ def convert_gather(self, op):
+ """Method to Convert TFLite Gather operator"""
+ # Check if the input tensor is quantized, call QNN op
+ if self.is_quantized(op):
+ raise tvm.error.OpNotImplemented(
+ 'TFlite quantized gather operator is not supported yet.')
Review comment:
Since this is a tensor manipulation operation rather than something that requires any specific qnn dialect, I would prefer we handle the qnn ops here.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
[GitHub] [incubator-tvm] wyc-ruiker commented on a change in pull request
#4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added
Posted by GitBox <gi...@apache.org>.
wyc-ruiker commented on a change in pull request #4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added
URL: https://github.com/apache/incubator-tvm/pull/4788#discussion_r374744847
##########
File path: tests/python/frontend/tflite/test_forward.py
##########
@@ -244,6 +244,74 @@ def test_forward_slice():
_test_slice(np.arange(8, dtype=np.int32).reshape((2, 4)), begin=[0, 1], size=[-1, -1])
_test_slice(np.arange(5, dtype=np.int32).reshape((5, )), begin=[4], size=[-1])
+#######################################################################
+# Gather
+# ------
+
+def _test_gather(dshape, indices, axis, dtype):
+ """ One iteration of Gather """
+ data = np.random.uniform(1, 10, size=dshape).astype(dtype)
+ indices = np.asarray(indices).astype('int32')
+
+ with tf.Graph().as_default():
+ in_data = array_ops.placeholder(shape=data.shape, dtype=data.dtype)
+ out = array_ops.gather(in_data, indices, axis=axis)
+ compare_tflite_with_tvm(data, 'Placeholder:0', [in_data], [out])
+
+ #Test quantized input
+ data = np.random.uniform(1, 10, size=dshape).astype(np.uint8)
+ with tf.Graph().as_default():
+ in_data = array_ops.placeholder(shape=data.shape, dtype=data.dtype, name="in_data")
+ out = array_ops.gather(in_data, indices, axis=axis)
+ compare_tflite_with_tvm([data], ['in_data:0'], [in_data], [out], quantized=True)
+
+def test_forward_gather():
+ """ GATHER """
+ _test_gather((4,), [1], 0, 'float32')
+ _test_gather((1, 4), [0], 0, 'int32')
+ _test_gather((4,), [[[1, 0], [0, 1]]], 0, 'float32')
+ _test_gather((2, 2), [[[1, 0], [0, 1]]], 0, 'int32')
+ _test_gather((2, 2), [[[1, 0], [0, 1]]], 1, 'int32')
+ _test_gather((2, 2), [[[1, 0], [0, 1]]], 0, 'float32')
+ _test_gather((3, 3, 3), [[[1, 0]]], 0, 'int32')
+ _test_gather((3, 3, 3), [[[1, 0]]], 2, 'int32')
+ _test_gather((4, 3, 5, 6), [[2, 1, 0, 0]], 0, 'float32')
+
+#######################################################################
+# StridedSlice
+# ------------
+
+def _test_stridedslice(ip_shape, begin, end, stride, dtype,
+ begin_mask=0, end_mask=0, new_axis_mask=0,
+ shrink_axis_mask=0, ellipsis_mask=0):
+ """ One iteration of a Stridedslice """
+ data = np.random.uniform(size=ip_shape).astype(dtype)
+ with tf.Graph().as_default():
+ in_data = tf.placeholder(dtype, ip_shape, name="in_data")
+ out = array_ops.strided_slice(in_data, begin, end, stride,
+ begin_mask=begin_mask,
+ end_mask=end_mask, new_axis_mask=new_axis_mask,
+ shrink_axis_mask=shrink_axis_mask,
+ ellipsis_mask=ellipsis_mask)
+ compare_tflite_with_tvm(data, 'in_data:0', [in_data], [out])
+
+ #Test with quantized inputs
+ data = np.random.uniform(size=ip_shape).astype(np.uint8)
+ with tf.Graph().as_default():
+ in_data = tf.placeholder(dtype, ip_shape, name="in_data")
+ out = array_ops.strided_slice(in_data, begin, end, stride,
+ begin_mask=begin_mask,
+ end_mask=end_mask, new_axis_mask=new_axis_mask,
+ shrink_axis_mask=shrink_axis_mask,
+ ellipsis_mask=ellipsis_mask)
+ compare_tflite_with_tvm([data], ['in_data:0'], [in_data], [out], quantized=True)
+
+def test_forward_stridedslice():
+ '''test StridedSlice'''
Review comment:
Is it necessary to move [all these tests](https://github.com/apache/incubator-tvm/blob/master/tests/python/frontend/tensorflow/test_forward.py#L1146) here? These unit tests don't cover all situations.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
[GitHub] [incubator-tvm] siju-samuel commented on a change in pull request
#4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added
Posted by GitBox <gi...@apache.org>.
siju-samuel commented on a change in pull request #4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added
URL: https://github.com/apache/incubator-tvm/pull/4788#discussion_r379762561
##########
File path: python/tvm/relay/frontend/tflite.py
##########
@@ -792,6 +794,147 @@ def convert_not_equal(self, op):
'TFlite quantized NOT_EQUAL operator is not supported yet.')
return self._convert_elemwise(_op.not_equal, op)
+ def convert_gather(self, op):
+ """Method to Convert TFLite GATHER operator"""
+ try:
+ from tflite.BuiltinOptions import BuiltinOptions
+ from tflite.GatherOptions import GatherOptions
+ from tflite.TensorType import TensorType
+ except ImportError:
+ raise ImportError("The tflite package must be installed")
+
+ input_tensors = self.get_input_tensors(op)
+ data = self.get_expr(input_tensors[0].tensor_idx)
+
+ indices = input_tensors[1]
+ indices_type = indices.tensor.Type()
+ assert indices_type in (TensorType.INT32, TensorType.INT64)
+ indices_type_str = self.get_tensor_type_str(indices_type)
+ indices = self.exp_tab.new_const(self.get_tensor_value(indices),
+ dtype=indices_type_str)
+
+ assert op.BuiltinOptionsType() == BuiltinOptions.GatherOptions
+ op_options = op.BuiltinOptions()
+ gather_options = GatherOptions()
+ gather_options.Init(op_options.Bytes, op_options.Pos)
+ axis = gather_options.Axis()
+
+ out = _op.take(data, indices, axis=axis)
+ return out
+
Review comment:
Added a comment explaining the same. The strided slice code is taken from tensorflow parsing code, kept the same code for now, so that when tflite upgrades, tvm donot need to update.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
[GitHub] [incubator-tvm] u99127 commented on a change in pull request #4788:
[FRONTEND][TFLITE]Gather, StridedSlice op support added
Posted by GitBox <gi...@apache.org>.
u99127 commented on a change in pull request #4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added
URL: https://github.com/apache/incubator-tvm/pull/4788#discussion_r381991135
##########
File path: python/tvm/relay/frontend/tflite.py
##########
@@ -852,6 +855,193 @@ def convert_logical_or(self, op):
"""Convert tflite LOGICAL_OR"""
return self._convert_logical_binary(_op.logical_or, op)
+ def convert_gather(self, op):
+ """Method to Convert TFLite GATHER operator"""
+ try:
+ from tflite.BuiltinOptions import BuiltinOptions
+ from tflite.GatherOptions import GatherOptions
+ from tflite.TensorType import TensorType
+ except ImportError:
+ raise ImportError("The tflite package must be installed")
+
+ input_tensors = self.get_input_tensors(op)
+ assert len(input_tensors) == 2, "input tensors length should be 2"
+
+ data = self.get_expr(input_tensors[0].tensor_idx)
+
+ indices = input_tensors[1]
+ indices_type = indices.tensor.Type()
+ assert indices_type in (TensorType.INT32, TensorType.INT64)
+ indices_type_str = self.get_tensor_type_str(indices_type)
+ indices = self.exp_tab.new_const(self.get_tensor_value(indices),
+ dtype=indices_type_str)
+
+ assert op.BuiltinOptionsType() == BuiltinOptions.GatherOptions
+ op_options = op.BuiltinOptions()
+ gather_options = GatherOptions()
+ gather_options.Init(op_options.Bytes, op_options.Pos)
+ axis = gather_options.Axis()
+
+ # Check the indices are oob, tflite is unpredictable in case of oob.
+ data_shape = list(input_tensors[0].tensor.ShapeAsNumpy())
+ data_dim = len(data_shape)
+
+ axis_n = axis
+ if axis_n < 0:
+ axis_n += axis_n + data_dim
+ assert axis_n >= 0, "Axis out of bounds"
+ assert axis_n < data_dim, "Axis out of bounds"
+
+ indices_val = self.get_tensor_value(input_tensors[1])
+ indices_shape = list(indices_val.shape)
+ indices_len = len(indices_shape)
+
+ out_shape = []
+ for i in range(data_dim):
+ if axis_n == i:
+ for j in range(indices_len):
+ out_shape.append(indices_shape[j])
+ else:
+ out_shape.append(data_shape[i])
+
+ loopover = [range(s) for s in out_shape]
+ for idx in list(itertools.product(*loopover)):
+ indices_position = [idx[j] for j in range(axis_n, axis_n+indices_len)]
+
+ real_indices = [idx[j] for j in range(axis_n)]
+ real_indices.append(indices_val[tuple(indices_position)])
+ real_indices.extend([idx[j] for j in range(axis_n + indices_len, len(idx))])
+ for r, d in zip(real_indices, data_shape):
+ if r >= d:
+ raise ValueError("TFLite out of bound indices are not supported.")
+
+ # Use mode as fast since already checked for oob.
+ out = _op.take(data, indices, axis=axis, mode="fast")
+ return out
+
+ def convert_strided_slice(self, op):
+ """Method to Convert TFLite STRIDED_SLICE operator.
+ Note: Eventhough tf2.0 supports begin_mask, end_mask, ellipsis_mask, new_axis_mask
+ and shrink_axis_mask, tflite doesn't support these and expect these values to be zero.
+ But in future, they may open up the mask implementation, so kept the implementation
+ same as tensorflow.
+ TVM Relay implementation of doesn't support mask, so the mask values are processed here
Review comment:
relay.op.strided_slice ?
Instead of "similar to tensorflow parsing" a bit more context would be better here about what is actually being done because it is not clear what exactly you refer to as there are no comments next to op.strided_slice in tensorflow.py ;)
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
[GitHub] [incubator-tvm] u99127 commented on a change in pull request #4788:
[FRONTEND][TFLITE]Gather, StridedSlice op support added
Posted by GitBox <gi...@apache.org>.
u99127 commented on a change in pull request #4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added
URL: https://github.com/apache/incubator-tvm/pull/4788#discussion_r372390838
##########
File path: python/tvm/relay/frontend/tflite.py
##########
@@ -747,6 +749,158 @@ def convert_squared_difference(self, op):
out = _op.power(difference, relay.const(2, exp_type))
return out
+ def convert_gather(self, op):
+ """Method to Convert TFLite Gather operator"""
+ # Check if the input tensor is quantized, call QNN op
+ if self.is_quantized(op):
+ raise tvm.error.OpNotImplemented(
+ 'TFlite quantized gather operator is not supported yet.')
+ input_tensors = self.get_input_tensors(op)
+
+ try:
+ from tflite.BuiltinOptions import BuiltinOptions
+ from tflite.GatherOptions import GatherOptions
+ from tflite.TensorType import TensorType
+ except ImportError:
+ raise ImportError("The tflite package must be installed")
+
+ assert op.BuiltinOptionsType() == BuiltinOptions.GatherOptions
+ op_options = op.BuiltinOptions()
+ gather_options = GatherOptions()
+ gather_options.Init(op_options.Bytes, op_options.Pos)
+ axis = gather_options.Axis()
+
+ data = self.get_expr(input_tensors[0].tensor_idx)
+
+ indices = input_tensors[1]
+ indices_type = indices.tensor.Type()
+
+ assert indices_type in (TensorType.INT32, TensorType.INT64)
+ indices_type_str = self.get_tensor_type_str(indices_type)
+ indices = self.exp_tab.new_const(self.get_tensor_value(indices),
+ dtype=indices_type_str)
+ out = _op.take(data, indices, axis=axis)
+ return out
+
+ def convert_strided_slice(self, op):
+ """Method to Convert TFLite Strided Slice operator"""
+ # Check if the input tensor is quantized, call QNN op
+ if self.is_quantized(op):
+ raise tvm.error.OpNotImplemented(
+ 'TFlite quantized strided slice operator is not supported yet.')
Review comment:
Same comment as above - this is a tensor manipulation op rather than anything that intrinsically requires quantization knowledge.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
[GitHub] [incubator-tvm] u99127 commented on a change in pull request #4788:
[FRONTEND][TFLITE]Gather, StridedSlice op support added
Posted by GitBox <gi...@apache.org>.
u99127 commented on a change in pull request #4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added
URL: https://github.com/apache/incubator-tvm/pull/4788#discussion_r374497747
##########
File path: tests/python/frontend/tflite/test_forward.py
##########
@@ -244,6 +244,74 @@ def test_forward_slice():
_test_slice(np.arange(8, dtype=np.int32).reshape((2, 4)), begin=[0, 1], size=[-1, -1])
_test_slice(np.arange(5, dtype=np.int32).reshape((5, )), begin=[4], size=[-1])
+#######################################################################
+# Gather
+# ------
+
+def _test_gather(dshape, indices, axis, dtype):
+ """ One iteration of Gather """
+ data = np.random.uniform(1, 10, size=dshape).astype(dtype)
+ indices = np.asarray(indices).astype('int32')
+
+ with tf.Graph().as_default():
+ in_data = array_ops.placeholder(shape=data.shape, dtype=data.dtype)
+ out = array_ops.gather(in_data, indices, axis=axis)
+ compare_tflite_with_tvm(data, 'Placeholder:0', [in_data], [out])
+
+ #Test quantized input
+ data = np.random.uniform(1, 10, size=dshape).astype(np.uint8)
+ with tf.Graph().as_default():
+ in_data = array_ops.placeholder(shape=data.shape, dtype=data.dtype, name="in_data")
+ out = array_ops.gather(in_data, indices, axis=axis)
+ compare_tflite_with_tvm([data], ['in_data:0'], [in_data], [out], quantized=True)
+
+def test_forward_gather():
+ """ GATHER """
+ _test_gather((4,), [1], 0, 'float32')
+ _test_gather((1, 4), [0], 0, 'int32')
+ _test_gather((4,), [[[1, 0], [0, 1]]], 0, 'float32')
+ _test_gather((2, 2), [[[1, 0], [0, 1]]], 0, 'int32')
+ _test_gather((2, 2), [[[1, 0], [0, 1]]], 1, 'int32')
+ _test_gather((2, 2), [[[1, 0], [0, 1]]], 0, 'float32')
+ _test_gather((3, 3, 3), [[[1, 0]]], 0, 'int32')
+ _test_gather((3, 3, 3), [[[1, 0]]], 2, 'int32')
+ _test_gather((4, 3, 5, 6), [[2, 1, 0, 0]], 0, 'float32')
Review comment:
I think a testcase is missing to test that out of bounds indices behave as tflite expects it to behave. See the documentation for relay.op.transform.take with the last optional parameter for "mode"
See here for more . https://docs.tvm.ai/api/python/relay/op.html
Further, axis is an optional input to gather in tflite and _op.take . Do the 2 semantics match up as I cannot see this obviously in the tflite documentation ?
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services
[GitHub] [incubator-tvm] FrozenGene commented on pull request #4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added
Posted by GitBox <gi...@apache.org>.
FrozenGene commented on pull request #4788:
URL: https://github.com/apache/incubator-tvm/pull/4788#issuecomment-618942742
Thanks @siju-samuel @wyc-ruiker @u99127
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org