onnx2tf 1.25.10__tar.gz → 1.25.12__tar.gz

{onnx2tf-1.25.10/onnx2tf.egg-info → onnx2tf-1.25.12}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: onnx2tf
-Version: 1.25.10
+Version: 1.25.12
 Summary: Self-Created Tools to convert ONNX files (NCHW) to TensorFlow/TFLite/Keras format (NHWC). The purpose of this tool is to solve the massive Transpose extrapolation problem in onnx-tensorflow (onnx-tf).
 Home-page: https://github.com/PINTO0309/onnx2tf
 Author: Katsuya Hyodo
@@ -314,7 +314,7 @@ Video speed is adjusted approximately 50 times slower than actual speed.
   docker run --rm -it \
   -v `pwd`:/workdir \
   -w /workdir \
-  ghcr.io/pinto0309/onnx2tf:1.25.10
+  ghcr.io/pinto0309/onnx2tf:1.25.12
 
   or
 
@@ -322,7 +322,7 @@ Video speed is adjusted approximately 50 times slower than actual speed.
   docker run --rm -it \
   -v `pwd`:/workdir \
   -w /workdir \
-  docker.io/pinto0309/onnx2tf:1.25.10
+  docker.io/pinto0309/onnx2tf:1.25.12
 
   or
 
@@ -419,7 +419,7 @@ The given SavedModel SignatureDef contains the following input(s):
 The given SavedModel SignatureDef contains the following output(s):
   outputs['output_0'] tensor_info:
       dtype: DT_FLOAT
-      shape: (1, 1000) # <-- Model design bug in resnet18-v1-7.onnx
+      shape: (-1, 1000)
       name: PartitionedCall:0
 Method name is: tensorflow/serving/predict
 

{onnx2tf-1.25.10 → onnx2tf-1.25.12}/README.md

@@ -299,7 +299,7 @@ Video speed is adjusted approximately 50 times slower than actual speed.
   docker run --rm -it \
   -v `pwd`:/workdir \
   -w /workdir \
-  ghcr.io/pinto0309/onnx2tf:1.25.10
+  ghcr.io/pinto0309/onnx2tf:1.25.12
 
   or
 
@@ -307,7 +307,7 @@ Video speed is adjusted approximately 50 times slower than actual speed.
   docker run --rm -it \
   -v `pwd`:/workdir \
   -w /workdir \
-  docker.io/pinto0309/onnx2tf:1.25.10
+  docker.io/pinto0309/onnx2tf:1.25.12
 
   or
 
@@ -404,7 +404,7 @@ The given SavedModel SignatureDef contains the following input(s):
 The given SavedModel SignatureDef contains the following output(s):
   outputs['output_0'] tensor_info:
       dtype: DT_FLOAT
-      shape: (1, 1000) # <-- Model design bug in resnet18-v1-7.onnx
+      shape: (-1, 1000)
       name: PartitionedCall:0
 Method name is: tensorflow/serving/predict
 

{onnx2tf-1.25.10 → onnx2tf-1.25.12}/onnx2tf/__init__.py

@@ -1,3 +1,3 @@
 from onnx2tf.onnx2tf import convert, main
 
-__version__ = '1.25.10'
+__version__ = '1.25.12'

{onnx2tf-1.25.10 → onnx2tf-1.25.12}/onnx2tf/ops/BatchNormalization.py

@@ -338,11 +338,17 @@ def make_node(
 
         # Automatic correction of accuracy degradation
         min_abs_err = sys.maxsize
-        min_abs_err_perm_1: List[int] = [idx for idx in range(len(mean.shape))]
+        min_abs_err_perm_1: List[int] = []
+        check_length = 0
+        if input_tensor.shape is not None and mean.shape is not None and len(input_tensor.shape) >= len(mean.shape):
+            check_length = len(input_tensor.shape)
+        else:
+            check_length = len(mean.shape)
+        min_abs_err_perm_1: List[int] = [idx for idx in range(check_length)]
 
         if not disable_strict_mode:
             if onnx_tensor_infos is not None and validation_data is not None:
-                tensor_1_candidate_for_transpositions = list(itertools.permutations(range(len(mean.shape))))
+                tensor_1_candidate_for_transpositions = list(itertools.permutations(range(check_length)))
                 # Search for the axis with the smallest error
                 for tensor_1_candidate_for_transposition in tensor_1_candidate_for_transpositions:
                     try:
@@ -470,71 +476,72 @@ def make_node(
                     except Exception as ex:
                         pass
 
-                tf_layers_dict[Y.name]['tf_node'] = \
-                    tf.nn.batch_normalization(
-                        x=input_tensor,
-                        mean=\
-                            transpose_with_flexing_deterrence(
-                                input_tensor=mean,
-                                perm=min_abs_err_perm_1,
-                                output_shape=Y.shape \
-                                    if None not in Y.shape and Y.shape != [] else None,
-                                **kwargs,
-                            ) if not isinstance(mean, np.ndarray) else \
-                            transpose_with_flexing_deterrence(
-                                input_tensor=tf.convert_to_tensor(mean),
-                                perm=min_abs_err_perm_1,
-                                output_shape=Y.shape \
-                                    if None not in Y.shape and Y.shape != [] else None,
-                                **kwargs,
-                            ),
-                        variance=\
-                            transpose_with_flexing_deterrence(
-                                input_tensor=var,
-                                perm=min_abs_err_perm_1,
-                                output_shape=Y.shape \
-                                    if None not in Y.shape and Y.shape != [] else None,
-                                **kwargs,
-                            ) if not isinstance(var, np.ndarray) else \
-                            transpose_with_flexing_deterrence(
-                                input_tensor=tf.convert_to_tensor(var),
-                                perm=min_abs_err_perm_1,
-                                output_shape=Y.shape \
-                                    if None not in Y.shape and Y.shape != [] else None,
-                                **kwargs,
-                            ),
-                        offset=\
-                            transpose_with_flexing_deterrence(
-                                input_tensor=offset,
-                                perm=min_abs_err_perm_1,
-                                output_shape=Y.shape \
-                                    if None not in Y.shape and Y.shape != [] else None,
-                                **kwargs,
-                            ) if not isinstance(offset, np.ndarray) else \
-                            transpose_with_flexing_deterrence(
-                                input_tensor=tf.convert_to_tensor(offset),
-                                perm=min_abs_err_perm_1,
-                                output_shape=Y.shape \
-                                    if None not in Y.shape and Y.shape != [] else None,
-                                **kwargs,
-                            ),
-                        scale=\
-                            transpose_with_flexing_deterrence(
-                                input_tensor=scale,
-                                perm=min_abs_err_perm_1,
-                                output_shape=Y.shape \
-                                    if None not in Y.shape and Y.shape != [] else None,
-                                **kwargs,
-                            ) if not isinstance(scale, np.ndarray) else \
-                            transpose_with_flexing_deterrence(
-                                input_tensor=tf.convert_to_tensor(scale),
-                                perm=min_abs_err_perm_1,
-                                output_shape=Y.shape \
-                                    if None not in Y.shape and Y.shape != [] else None,
-                                **kwargs,
-                            ),
-                        variance_epsilon=epsilon,
-                    )
+                if min_abs_err_perm_1 != [idx for idx in range(check_length)]:
+                    tf_layers_dict[Y.name]['tf_node'] = \
+                        tf.nn.batch_normalization(
+                            x=input_tensor,
+                            mean=\
+                                transpose_with_flexing_deterrence(
+                                    input_tensor=mean,
+                                    perm=min_abs_err_perm_1,
+                                    output_shape=Y.shape \
+                                        if None not in Y.shape and Y.shape != [] else None,
+                                    **kwargs,
+                                ) if not isinstance(mean, np.ndarray) else \
+                                transpose_with_flexing_deterrence(
+                                    input_tensor=tf.convert_to_tensor(mean),
+                                    perm=min_abs_err_perm_1,
+                                    output_shape=Y.shape \
+                                        if None not in Y.shape and Y.shape != [] else None,
+                                    **kwargs,
+                                ),
+                            variance=\
+                                transpose_with_flexing_deterrence(
+                                    input_tensor=var,
+                                    perm=min_abs_err_perm_1,
+                                    output_shape=Y.shape \
+                                        if None not in Y.shape and Y.shape != [] else None,
+                                    **kwargs,
+                                ) if not isinstance(var, np.ndarray) else \
+                                transpose_with_flexing_deterrence(
+                                    input_tensor=tf.convert_to_tensor(var),
+                                    perm=min_abs_err_perm_1,
+                                    output_shape=Y.shape \
+                                        if None not in Y.shape and Y.shape != [] else None,
+                                    **kwargs,
+                                ),
+                            offset=\
+                                transpose_with_flexing_deterrence(
+                                    input_tensor=offset,
+                                    perm=min_abs_err_perm_1,
+                                    output_shape=Y.shape \
+                                        if None not in Y.shape and Y.shape != [] else None,
+                                    **kwargs,
+                                ) if not isinstance(offset, np.ndarray) else \
+                                transpose_with_flexing_deterrence(
+                                    input_tensor=tf.convert_to_tensor(offset),
+                                    perm=min_abs_err_perm_1,
+                                    output_shape=Y.shape \
+                                        if None not in Y.shape and Y.shape != [] else None,
+                                    **kwargs,
+                                ),
+                            scale=\
+                                transpose_with_flexing_deterrence(
+                                    input_tensor=scale,
+                                    perm=min_abs_err_perm_1,
+                                    output_shape=Y.shape \
+                                        if None not in Y.shape and Y.shape != [] else None,
+                                    **kwargs,
+                                ) if not isinstance(scale, np.ndarray) else \
+                                transpose_with_flexing_deterrence(
+                                    input_tensor=tf.convert_to_tensor(scale),
+                                    perm=min_abs_err_perm_1,
+                                    output_shape=Y.shape \
+                                        if None not in Y.shape and Y.shape != [] else None,
+                                    **kwargs,
+                                ),
+                            variance_epsilon=epsilon,
+                        )
                 tf_type = tf.nn.batch_normalization
 
     # Post-process transpose

{onnx2tf-1.25.10 → onnx2tf-1.25.12}/onnx2tf/ops/Flatten.py

@@ -57,14 +57,17 @@ def make_node(
     output_shape = graph_node_output.shape
     dtype = graph_node_output.dtype
 
-    axis = graph_node.attrs.get("axis", 0)
-    if graph_node_input.shape is not None \
-        and axis < input_tensor_rank:
-        axis = convert_axis(
-            axis=axis,
-            tensor_rank=len(graph_node_input.shape),
-            before_op_output_shape_trans=before_op_output_shape_trans,
-        )
+    axis = graph_node.attrs.get("axis", None)
+    if axis is not None:
+        if graph_node_input.shape is not None \
+            and axis < input_tensor_rank:
+            axis = convert_axis(
+                axis=axis,
+                tensor_rank=len(graph_node_input.shape),
+                before_op_output_shape_trans=before_op_output_shape_trans,
+            )
+    else:
+        axis = input_tensor_rank - 1
 
     # Preserving Graph Structure (Dict)
     tf_layers_dict[graph_node_output.name] = {

{onnx2tf-1.25.10 → onnx2tf-1.25.12/onnx2tf.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: onnx2tf
-Version: 1.25.10
+Version: 1.25.12
 Summary: Self-Created Tools to convert ONNX files (NCHW) to TensorFlow/TFLite/Keras format (NHWC). The purpose of this tool is to solve the massive Transpose extrapolation problem in onnx-tensorflow (onnx-tf).
 Home-page: https://github.com/PINTO0309/onnx2tf
 Author: Katsuya Hyodo
@@ -314,7 +314,7 @@ Video speed is adjusted approximately 50 times slower than actual speed.
   docker run --rm -it \
   -v `pwd`:/workdir \
   -w /workdir \
-  ghcr.io/pinto0309/onnx2tf:1.25.10
+  ghcr.io/pinto0309/onnx2tf:1.25.12
 
   or
 
@@ -322,7 +322,7 @@ Video speed is adjusted approximately 50 times slower than actual speed.
   docker run --rm -it \
   -v `pwd`:/workdir \
   -w /workdir \
-  docker.io/pinto0309/onnx2tf:1.25.10
+  docker.io/pinto0309/onnx2tf:1.25.12
 
   or
 
@@ -419,7 +419,7 @@ The given SavedModel SignatureDef contains the following input(s):
 The given SavedModel SignatureDef contains the following output(s):
   outputs['output_0'] tensor_info:
       dtype: DT_FLOAT
-      shape: (1, 1000) # <-- Model design bug in resnet18-v1-7.onnx
+      shape: (-1, 1000)
       name: PartitionedCall:0
 Method name is: tensorflow/serving/predict