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

Added support for int64 -> string CategoryMapper updated #2181

Merged
merged 7 commits into from
May 30, 2023
Merged

Added support for int64 -> string CategoryMapper updated #2181

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
634092c
add int64->string support
pagran May 28, 2023
a93e26d
fix lint
pagran May 28, 2023
40a01c9
fix lint
pagran May 28, 2023
c0d62f1
fix lint
pagran May 28, 2023
1c5b704
Merge branch 'main' into int2str
pagran May 29, 2023
80a238a
Merge branch 'main' into int2str
fatcat-z May 30, 2023
0d22912
move out of block
pagran May 30, 2023
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
36 changes: 36 additions & 0 deletions tests/test_backend.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5440,6 +5440,24 @@ def func(query_holder):
self._run_test_case(func, [_OUTPUT], {_INPUT: query}, as_session=True)
os.remove(filnm)

@check_opset_min_version(8, "CategoryMapper")
@skip_tfjs("TFJS does not initialize table")
@skip_onnx_checker("ONNX can't do type inference on CategoryMapper")
def test_hashtable_lookup_invert(self):
filnm = "vocab.tmp"
words = ["apple", "pear", "banana", "cherry", "grape"]
query = np.array([3], dtype=np.int64)
with open(filnm, "w") as f:
for word in words:
f.write(word + "\n")
def func(query_holder):
hash_table = lookup_ops.index_to_string_table_from_file(filnm)
lookup_results = hash_table.lookup(query_holder)
ret = tf.identity(lookup_results, name=_TFOUTPUT)
return ret
self._run_test_case(func, [_OUTPUT], {_INPUT: query}, as_session=True)
os.remove(filnm)

@check_opset_min_version(8, "CategoryMapper")
@skip_tfjs("TFJS does not initialize table")
def test_hashtable_lookup_const(self):
Expand All @@ -5458,6 +5476,24 @@ def func():
self._run_test_case(func, [_OUTPUT], {}, as_session=True)
os.remove(filnm)

@check_opset_min_version(8, "CategoryMapper")
@skip_tfjs("TFJS does not initialize table")
def test_hashtable_lookup_invert_const(self):
filnm = "vocab.tmp"
words = ["apple", "pear", "banana", "cherry", "grape"]
query_val = np.array([3, 2], dtype=np.int64).reshape((1, 2, 1))
with open(filnm, "w", encoding='UTF-8') as f:
for word in words:
f.write(word + "\n")
def func():
hash_table = lookup_ops.index_to_string_table_from_file(filnm)
query = tf.constant(query_val)
lookup_results = hash_table.lookup(query)
ret = tf.identity(lookup_results, name=_TFOUTPUT)
return ret
self._run_test_case(func, [_OUTPUT], {}, as_session=True)
os.remove(filnm)

@skip_tfjs("TFJS does not initialize table")
def test_hashtable_size(self):
filnm = "vocab.tmp"
Expand Down
27 changes: 18 additions & 9 deletions tf2onnx/custom_opsets/onnx_ml.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,10 +42,18 @@ def version_8(cls, ctx, node, initialized_tables, **kwargs):

dtype = ctx.get_dtype(node.output[0])
in_dtype = ctx.get_dtype(node.input[1])
utils.make_sure(dtype == TensorProto.INT64 and in_dtype == TensorProto.STRING,
"Only lookup tables of type string->int64 are currently supported.")
utils.make_sure((dtype == TensorProto.INT64 and in_dtype == TensorProto.STRING) or
(dtype == TensorProto.STRING and in_dtype == TensorProto.INT64),
f"Only lookup tables of type string<->int64 are currently supported.")

if in_dtype == TensorProto.STRING:
cats_strings, cats_int64s = initialized_tables[shared_name]
default_key = 'default_int64'
else:
cats_int64s, cats_strings = initialized_tables[shared_name]
default_key = 'default_string'
attr = {'cats_int64s': cats_int64s, 'cats_strings': cats_strings, default_key: default_val}

cats_strings, cats_int64s = initialized_tables[shared_name]
shape = ctx.get_shape(node.input[1])

node_name = node.name
Expand All @@ -56,18 +64,19 @@ def version_8(cls, ctx, node, initialized_tables, **kwargs):
# Handle explicitly since const folding doesn't work for tables
key_np = node.inputs[1].get_tensor_value(as_list=False)
ctx.remove_node(node.name)
key_to_val = dict(zip(cats_strings, cats_int64s))
def lookup_value(key):
return key_to_val.get(key.encode("UTF-8"), default_val_np)
lookup_result = np.vectorize(lookup_value)(key_np)
if in_dtype == TensorProto.STRING:
key_to_val = dict(zip(cats_strings, cats_int64s))
lookup_result = np.vectorize(lambda key: key_to_val.get(key.encode("UTF-8"), default_val_np))(key_np)
else:
key_to_val = dict(zip(cats_int64s, cats_strings))
lookup_result = np.vectorize(lambda key: key_to_val.get(key, default_val_np))(key_np).astype(object)
onnx_tensor = numpy_helper.from_array(lookup_result, node_name)
ctx.make_node("Const", name=node_name, inputs=[], outputs=node_outputs,
attr={"value": onnx_tensor}, shapes=[lookup_result.shape], dtypes=[dtype])
else:
ctx.remove_node(node.name)
ctx.make_node("CategoryMapper", domain=constants.AI_ONNX_ML_DOMAIN,
name=node_name, inputs=[node_inputs[1]], outputs=node_outputs,
attr={'cats_int64s': cats_int64s, 'cats_strings': cats_strings, 'default_int64': default_val},
name=node_name, inputs=[node_inputs[1]], outputs=node_outputs, attr=attr,
shapes=[shape], dtypes=[dtype])

customer_nodes = ctx.find_output_consumers(table_node.output[0])
Expand Down