onnx2tf 1.29.3__tar.gz → 1.29.4__tar.gz

{onnx2tf-1.29.3/onnx2tf.egg-info → onnx2tf-1.29.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: onnx2tf
-Version: 1.29.3
+Version: 1.29.4
 Summary: Self-Created Tools to convert ONNX files (NCHW) to TensorFlow/TFLite/Keras format (NHWC).
 Home-page: https://github.com/PINTO0309/onnx2tf
 Author: Katsuya Hyodo
@@ -106,10 +106,10 @@ https://github.com/PINTO0309/onnx2tf/wiki/model_status
   |BatchNormalization|:heavy_check_mark:|
   |Bernoulli|:heavy_check_mark:|
   |BitShift|:heavy_check_mark:|
-  |BitwiseAnd|**Help wanted**|
-  |BitwiseNot|**Help wanted**|
-  |BitwiseOr|**Help wanted**|
-  |BitwiseXor|**Help wanted**|
+  |BitwiseAnd|:heavy_check_mark:|
+  |BitwiseNot|:heavy_check_mark:|
+  |BitwiseOr|:heavy_check_mark:|
+  |BitwiseXor|:heavy_check_mark:|
   |Cast|:heavy_check_mark:|
   |Ceil|:heavy_check_mark:|
   |Celu|:heavy_check_mark:|
@@ -345,7 +345,7 @@ Video speed is adjusted approximately 50 times slower than actual speed.
   docker run --rm -it \
   -v `pwd`:/workdir \
   -w /workdir \
-  ghcr.io/pinto0309/onnx2tf:1.29.3
+  ghcr.io/pinto0309/onnx2tf:1.29.4
 
   or
 
@@ -353,7 +353,7 @@ Video speed is adjusted approximately 50 times slower than actual speed.
   docker run --rm -it \
   -v `pwd`:/workdir \
   -w /workdir \
-  docker.io/pinto0309/onnx2tf:1.29.3
+  docker.io/pinto0309/onnx2tf:1.29.4
 
   or
 

{onnx2tf-1.29.3 → onnx2tf-1.29.4}/README.md

@@ -70,10 +70,10 @@ https://github.com/PINTO0309/onnx2tf/wiki/model_status
   |BatchNormalization|:heavy_check_mark:|
   |Bernoulli|:heavy_check_mark:|
   |BitShift|:heavy_check_mark:|
-  |BitwiseAnd|**Help wanted**|
-  |BitwiseNot|**Help wanted**|
-  |BitwiseOr|**Help wanted**|
-  |BitwiseXor|**Help wanted**|
+  |BitwiseAnd|:heavy_check_mark:|
+  |BitwiseNot|:heavy_check_mark:|
+  |BitwiseOr|:heavy_check_mark:|
+  |BitwiseXor|:heavy_check_mark:|
   |Cast|:heavy_check_mark:|
   |Ceil|:heavy_check_mark:|
   |Celu|:heavy_check_mark:|
@@ -309,7 +309,7 @@ Video speed is adjusted approximately 50 times slower than actual speed.
   docker run --rm -it \
   -v `pwd`:/workdir \
   -w /workdir \
-  ghcr.io/pinto0309/onnx2tf:1.29.3
+  ghcr.io/pinto0309/onnx2tf:1.29.4
 
   or
 
@@ -317,7 +317,7 @@ Video speed is adjusted approximately 50 times slower than actual speed.
   docker run --rm -it \
   -v `pwd`:/workdir \
   -w /workdir \
-  docker.io/pinto0309/onnx2tf:1.29.3
+  docker.io/pinto0309/onnx2tf:1.29.4
 
   or
 

{onnx2tf-1.29.3 → onnx2tf-1.29.4}/onnx2tf/__init__.py

@@ -1,3 +1,3 @@
 from onnx2tf.onnx2tf import convert, main
 
-__version__ = '1.29.3'
+__version__ = '1.29.4'

onnx2tf-1.29.4/onnx2tf/ops/BitwiseAnd.py

@@ -0,0 +1,115 @@
+import random
+random.seed(0)
+import numpy as np
+np.random.seed(0)
+import tensorflow as tf
+import onnx_graphsurgeon as gs
+from onnx2tf.utils.common_functions import (
+    get_constant_or_variable,
+    print_node_info,
+    inverted_operation_enable_disable,
+    make_tf_node_info,
+    get_replacement_parameter,
+    pre_process_transpose,
+    post_process_transpose,
+)
+
+
+@print_node_info
+@inverted_operation_enable_disable
+@get_replacement_parameter
+def make_node(
+    *,
+    graph_node: gs.Node,
+    tf_layers_dict: dict,
+    **kwargs: dict,
+):
+    """BitwiseAnd
+
+    Parameters
+    ----------
+    graph_node: gs.Node
+        graph_surgeon Node
+
+    tf_layers_dict: dict
+        optype, shape, dtype, tensorflow graph
+    """
+    before_op_output_shape_trans_1 = \
+        tf_layers_dict.get(graph_node.inputs[0].name, {}).get('before_op_output_shape_trans', True)
+    before_op_output_shape_trans_2 = \
+        tf_layers_dict.get(graph_node.inputs[1].name, {}).get('before_op_output_shape_trans', True)
+    before_op_output_shape_trans = \
+        before_op_output_shape_trans_1 \
+        and before_op_output_shape_trans_2
+
+    graph_node_input_1 = get_constant_or_variable(
+        graph_node.inputs[0],
+        before_op_output_shape_trans,
+    )
+    graph_node_input_2 = get_constant_or_variable(
+        graph_node.inputs[1],
+        before_op_output_shape_trans,
+    )
+    graph_node_output: gs.Variable = graph_node.outputs[0]
+
+    shape = graph_node_output.shape
+    dtype = graph_node_output.dtype
+
+    # Preserving Graph Structure (Dict)
+    tf_layers_dict[graph_node_output.name] = {
+        'optype': graph_node.op,
+        'shape': shape,
+        'dtype': dtype,
+    }
+
+    # Generation of TF OP
+    input_tensor_1 = tf_layers_dict[graph_node_input_1.name]['tf_node'] \
+        if isinstance(graph_node_input_1, gs.Variable) else graph_node_input_1
+    input_tensor_2 = tf_layers_dict[graph_node_input_2.name]['tf_node'] \
+        if isinstance(graph_node_input_2, gs.Variable) else graph_node_input_2
+
+    # Pre-process transpose
+    input_tensor_1 = pre_process_transpose(
+        value_before_transpose=input_tensor_1,
+        param_target='inputs',
+        param_name=graph_node.inputs[0].name,
+        **kwargs,
+    )
+    input_tensor_2 = pre_process_transpose(
+        value_before_transpose=input_tensor_2,
+        param_target='inputs',
+        param_name=graph_node.inputs[1].name,
+        **kwargs,
+    )
+
+    tf_op_type = None
+    tf_layers_dict[graph_node_output.name]['tf_node'] = \
+        tf.bitwise.bitwise_and(
+            x=input_tensor_1,
+            y=input_tensor_2,
+            name=graph_node.name,
+        )
+    tf_op_type = tf.bitwise.bitwise_and
+
+    # Post-process transpose
+    tf_layers_dict[graph_node_output.name]['tf_node'] = post_process_transpose(
+        value_before_transpose=tf_layers_dict[graph_node_output.name]['tf_node'],
+        param_target='outputs',
+        param_name=graph_node.outputs[0].name,
+        **kwargs,
+    )
+
+    # Generation of Debug Info
+    tf_layers_dict[graph_node_output.name]['tf_node_info'] = \
+        make_tf_node_info(
+            node_info={
+                'tf_op_type': tf_op_type,
+                'tf_inputs': {
+                    'x': input_tensor_1,
+                    'y': input_tensor_2,
+                },
+                'tf_outputs': {
+                    'output': tf_layers_dict[graph_node_output.name]['tf_node'],
+                },
+            }
+        )

onnx2tf-1.29.4/onnx2tf/ops/BitwiseNot.py

@@ -0,0 +1,98 @@
+import random
+random.seed(0)
+import numpy as np
+np.random.seed(0)
+import tensorflow as tf
+import onnx_graphsurgeon as gs
+from onnx2tf.utils.common_functions import (
+    get_constant_or_variable,
+    print_node_info,
+    inverted_operation_enable_disable,
+    make_tf_node_info,
+    get_replacement_parameter,
+    pre_process_transpose,
+    post_process_transpose,
+)
+
+
+@print_node_info
+@inverted_operation_enable_disable
+@get_replacement_parameter
+def make_node(
+    *,
+    graph_node: gs.Node,
+    tf_layers_dict: dict,
+    **kwargs: dict,
+):
+    """BitwiseNot
+
+    Parameters
+    ----------
+    graph_node: gs.Node
+        graph_surgeon Node
+
+    tf_layers_dict: dict
+        optype, shape, dtype, tensorflow graph
+    """
+    before_op_output_shape_trans_1 = \
+        tf_layers_dict.get(graph_node.inputs[0].name, {}).get('before_op_output_shape_trans', True)
+    before_op_output_shape_trans = \
+        before_op_output_shape_trans_1
+
+    graph_node_input_1 = get_constant_or_variable(
+        graph_node.inputs[0],
+        before_op_output_shape_trans,
+    )
+    graph_node_output: gs.Variable = graph_node.outputs[0]
+
+    shape = graph_node_output.shape
+    dtype = graph_node_output.dtype
+
+    # Preserving Graph Structure (Dict)
+    tf_layers_dict[graph_node_output.name] = {
+        'optype': graph_node.op,
+        'shape': shape,
+        'dtype': dtype,
+    }
+
+    # Generation of TF OP
+    input_tensor_1 = tf_layers_dict[graph_node_input_1.name]['tf_node'] \
+        if isinstance(graph_node_input_1, gs.Variable) else graph_node_input_1
+
+    # Pre-process transpose
+    input_tensor_1 = pre_process_transpose(
+        value_before_transpose=input_tensor_1,
+        param_target='inputs',
+        param_name=graph_node.inputs[0].name,
+        **kwargs,
+    )
+
+    tf_op_type = None
+    tf_layers_dict[graph_node_output.name]['tf_node'] = \
+        tf.bitwise.invert(
+            x=input_tensor_1,
+            name=graph_node.name,
+        )
+    tf_op_type = tf.bitwise.invert
+
+    # Post-process transpose
+    tf_layers_dict[graph_node_output.name]['tf_node'] = post_process_transpose(
+        value_before_transpose=tf_layers_dict[graph_node_output.name]['tf_node'],
+        param_target='outputs',
+        param_name=graph_node.outputs[0].name,
+        **kwargs,
+    )
+
+    # Generation of Debug Info
+    tf_layers_dict[graph_node_output.name]['tf_node_info'] = \
+        make_tf_node_info(
+            node_info={
+                'tf_op_type': tf_op_type,
+                'tf_inputs': {
+                    'x': input_tensor_1,
+                },
+                'tf_outputs': {
+                    'output': tf_layers_dict[graph_node_output.name]['tf_node'],
+                },
+            }
+        )

onnx2tf-1.29.4/onnx2tf/ops/BitwiseOr.py

@@ -0,0 +1,115 @@
+import random
+random.seed(0)
+import numpy as np
+np.random.seed(0)
+import tensorflow as tf
+import onnx_graphsurgeon as gs
+from onnx2tf.utils.common_functions import (
+    get_constant_or_variable,
+    print_node_info,
+    inverted_operation_enable_disable,
+    make_tf_node_info,
+    get_replacement_parameter,
+    pre_process_transpose,
+    post_process_transpose,
+)
+
+
+@print_node_info
+@inverted_operation_enable_disable
+@get_replacement_parameter
+def make_node(
+    *,
+    graph_node: gs.Node,
+    tf_layers_dict: dict,
+    **kwargs: dict,
+):
+    """BitwiseOr
+
+    Parameters
+    ----------
+    graph_node: gs.Node
+        graph_surgeon Node
+
+    tf_layers_dict: dict
+        optype, shape, dtype, tensorflow graph
+    """
+    before_op_output_shape_trans_1 = \
+        tf_layers_dict.get(graph_node.inputs[0].name, {}).get('before_op_output_shape_trans', True)
+    before_op_output_shape_trans_2 = \
+        tf_layers_dict.get(graph_node.inputs[1].name, {}).get('before_op_output_shape_trans', True)
+    before_op_output_shape_trans = \
+        before_op_output_shape_trans_1 \
+        and before_op_output_shape_trans_2
+
+    graph_node_input_1 = get_constant_or_variable(
+        graph_node.inputs[0],
+        before_op_output_shape_trans,
+    )
+    graph_node_input_2 = get_constant_or_variable(
+        graph_node.inputs[1],
+        before_op_output_shape_trans,
+    )
+    graph_node_output: gs.Variable = graph_node.outputs[0]
+
+    shape = graph_node_output.shape
+    dtype = graph_node_output.dtype
+
+    # Preserving Graph Structure (Dict)
+    tf_layers_dict[graph_node_output.name] = {
+        'optype': graph_node.op,
+        'shape': shape,
+        'dtype': dtype,
+    }
+
+    # Generation of TF OP
+    input_tensor_1 = tf_layers_dict[graph_node_input_1.name]['tf_node'] \
+        if isinstance(graph_node_input_1, gs.Variable) else graph_node_input_1
+    input_tensor_2 = tf_layers_dict[graph_node_input_2.name]['tf_node'] \
+        if isinstance(graph_node_input_2, gs.Variable) else graph_node_input_2
+
+    # Pre-process transpose
+    input_tensor_1 = pre_process_transpose(
+        value_before_transpose=input_tensor_1,
+        param_target='inputs',
+        param_name=graph_node.inputs[0].name,
+        **kwargs,
+    )
+    input_tensor_2 = pre_process_transpose(
+        value_before_transpose=input_tensor_2,
+        param_target='inputs',
+        param_name=graph_node.inputs[1].name,
+        **kwargs,
+    )
+
+    tf_op_type = None
+    tf_layers_dict[graph_node_output.name]['tf_node'] = \
+        tf.bitwise.bitwise_or(
+            x=input_tensor_1,
+            y=input_tensor_2,
+            name=graph_node.name,
+        )
+    tf_op_type = tf.bitwise.bitwise_or
+
+    # Post-process transpose
+    tf_layers_dict[graph_node_output.name]['tf_node'] = post_process_transpose(
+        value_before_transpose=tf_layers_dict[graph_node_output.name]['tf_node'],
+        param_target='outputs',
+        param_name=graph_node.outputs[0].name,
+        **kwargs,
+    )
+
+    # Generation of Debug Info
+    tf_layers_dict[graph_node_output.name]['tf_node_info'] = \
+        make_tf_node_info(
+            node_info={
+                'tf_op_type': tf_op_type,
+                'tf_inputs': {
+                    'x': input_tensor_1,
+                    'y': input_tensor_2,
+                },
+                'tf_outputs': {
+                    'output': tf_layers_dict[graph_node_output.name]['tf_node'],
+                },
+            }
+        )

onnx2tf-1.29.4/onnx2tf/ops/BitwiseXor.py

@@ -0,0 +1,115 @@
+import random
+random.seed(0)
+import numpy as np
+np.random.seed(0)
+import tensorflow as tf
+import onnx_graphsurgeon as gs
+from onnx2tf.utils.common_functions import (
+    get_constant_or_variable,
+    print_node_info,
+    inverted_operation_enable_disable,
+    make_tf_node_info,
+    get_replacement_parameter,
+    pre_process_transpose,
+    post_process_transpose,
+)
+
+
+@print_node_info
+@inverted_operation_enable_disable
+@get_replacement_parameter
+def make_node(
+    *,
+    graph_node: gs.Node,
+    tf_layers_dict: dict,
+    **kwargs: dict,
+):
+    """BitwiseXor
+
+    Parameters
+    ----------
+    graph_node: gs.Node
+        graph_surgeon Node
+
+    tf_layers_dict: dict
+        optype, shape, dtype, tensorflow graph
+    """
+    before_op_output_shape_trans_1 = \
+        tf_layers_dict.get(graph_node.inputs[0].name, {}).get('before_op_output_shape_trans', True)
+    before_op_output_shape_trans_2 = \
+        tf_layers_dict.get(graph_node.inputs[1].name, {}).get('before_op_output_shape_trans', True)
+    before_op_output_shape_trans = \
+        before_op_output_shape_trans_1 \
+        and before_op_output_shape_trans_2
+
+    graph_node_input_1 = get_constant_or_variable(
+        graph_node.inputs[0],
+        before_op_output_shape_trans,
+    )
+    graph_node_input_2 = get_constant_or_variable(
+        graph_node.inputs[1],
+        before_op_output_shape_trans,
+    )
+    graph_node_output: gs.Variable = graph_node.outputs[0]
+
+    shape = graph_node_output.shape
+    dtype = graph_node_output.dtype
+
+    # Preserving Graph Structure (Dict)
+    tf_layers_dict[graph_node_output.name] = {
+        'optype': graph_node.op,
+        'shape': shape,
+        'dtype': dtype,
+    }
+
+    # Generation of TF OP
+    input_tensor_1 = tf_layers_dict[graph_node_input_1.name]['tf_node'] \
+        if isinstance(graph_node_input_1, gs.Variable) else graph_node_input_1
+    input_tensor_2 = tf_layers_dict[graph_node_input_2.name]['tf_node'] \
+        if isinstance(graph_node_input_2, gs.Variable) else graph_node_input_2
+
+    # Pre-process transpose
+    input_tensor_1 = pre_process_transpose(
+        value_before_transpose=input_tensor_1,
+        param_target='inputs',
+        param_name=graph_node.inputs[0].name,
+        **kwargs,
+    )
+    input_tensor_2 = pre_process_transpose(
+        value_before_transpose=input_tensor_2,
+        param_target='inputs',
+        param_name=graph_node.inputs[1].name,
+        **kwargs,
+    )
+
+    tf_op_type = None
+    tf_layers_dict[graph_node_output.name]['tf_node'] = \
+        tf.bitwise.bitwise_xor(
+            x=input_tensor_1,
+            y=input_tensor_2,
+            name=graph_node.name,
+        )
+    tf_op_type = tf.bitwise.bitwise_xor
+
+    # Post-process transpose
+    tf_layers_dict[graph_node_output.name]['tf_node'] = post_process_transpose(
+        value_before_transpose=tf_layers_dict[graph_node_output.name]['tf_node'],
+        param_target='outputs',
+        param_name=graph_node.outputs[0].name,
+        **kwargs,
+    )
+
+    # Generation of Debug Info
+    tf_layers_dict[graph_node_output.name]['tf_node_info'] = \
+        make_tf_node_info(
+            node_info={
+                'tf_op_type': tf_op_type,
+                'tf_inputs': {
+                    'x': input_tensor_1,
+                    'y': input_tensor_2,
+                },
+                'tf_outputs': {
+                    'output': tf_layers_dict[graph_node_output.name]['tf_node'],
+                },
+            }
+        )

{onnx2tf-1.29.3 → onnx2tf-1.29.4/onnx2tf.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: onnx2tf
-Version: 1.29.3
+Version: 1.29.4
 Summary: Self-Created Tools to convert ONNX files (NCHW) to TensorFlow/TFLite/Keras format (NHWC).
 Home-page: https://github.com/PINTO0309/onnx2tf
 Author: Katsuya Hyodo
@@ -106,10 +106,10 @@ https://github.com/PINTO0309/onnx2tf/wiki/model_status
   |BatchNormalization|:heavy_check_mark:|
   |Bernoulli|:heavy_check_mark:|
   |BitShift|:heavy_check_mark:|
-  |BitwiseAnd|**Help wanted**|
-  |BitwiseNot|**Help wanted**|
-  |BitwiseOr|**Help wanted**|
-  |BitwiseXor|**Help wanted**|
+  |BitwiseAnd|:heavy_check_mark:|
+  |BitwiseNot|:heavy_check_mark:|
+  |BitwiseOr|:heavy_check_mark:|
+  |BitwiseXor|:heavy_check_mark:|
   |Cast|:heavy_check_mark:|
   |Ceil|:heavy_check_mark:|
   |Celu|:heavy_check_mark:|
@@ -345,7 +345,7 @@ Video speed is adjusted approximately 50 times slower than actual speed.
   docker run --rm -it \
   -v `pwd`:/workdir \
   -w /workdir \
-  ghcr.io/pinto0309/onnx2tf:1.29.3
+  ghcr.io/pinto0309/onnx2tf:1.29.4
 
   or
 
@@ -353,7 +353,7 @@ Video speed is adjusted approximately 50 times slower than actual speed.
   docker run --rm -it \
   -v `pwd`:/workdir \
   -w /workdir \
-  docker.io/pinto0309/onnx2tf:1.29.3
+  docker.io/pinto0309/onnx2tf:1.29.4
 
   or
 

{onnx2tf-1.29.3 → onnx2tf-1.29.4}/onnx2tf.egg-info/SOURCES.txt

@@ -26,6 +26,10 @@ onnx2tf/ops/AveragePool.py
 onnx2tf/ops/BatchNormalization.py
 onnx2tf/ops/Bernoulli.py
 onnx2tf/ops/BitShift.py
+onnx2tf/ops/BitwiseAnd.py
+onnx2tf/ops/BitwiseNot.py
+onnx2tf/ops/BitwiseOr.py
+onnx2tf/ops/BitwiseXor.py
 onnx2tf/ops/Cast.py
 onnx2tf/ops/Ceil.py
 onnx2tf/ops/Celu.py

{onnx2tf-1.29.3 → onnx2tf-1.29.4}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "onnx2tf"
-version = "1.29.3"
+version = "1.29.4"
 description = "Self-Created Tools to convert ONNX files (NCHW) to TensorFlow/TFLite/Keras format (NHWC)."
 readme = "README.md"
 requires-python = "==3.11.12"