onnx2tf 1.25.8__tar.gz → 1.25.10__tar.gz

{onnx2tf-1.25.8/onnx2tf.egg-info → onnx2tf-1.25.10}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: onnx2tf
-Version: 1.25.8
+Version: 1.25.10
 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:1.25.8
+  ghcr.io/pinto0309/onnx2tf:1.25.10
 
   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:1.25.8
+  docker.io/pinto0309/onnx2tf:1.25.10
 
   or
 

{onnx2tf-1.25.8 → onnx2tf-1.25.10}/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:1.25.8
+  ghcr.io/pinto0309/onnx2tf:1.25.10
 
   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:1.25.8
+  docker.io/pinto0309/onnx2tf:1.25.10
 
   or
 

{onnx2tf-1.25.8 → onnx2tf-1.25.10}/onnx2tf/__init__.py

@@ -1,3 +1,3 @@
 from onnx2tf.onnx2tf import convert, main
 
-__version__ = '1.25.8'
+__version__ = '1.25.10'

{onnx2tf-1.25.8 → onnx2tf-1.25.10}/onnx2tf/ops/Flatten.py

@@ -87,8 +87,20 @@ def make_node(
         cal_shape = (1, -1)
     elif axis >= input_tensor_rank:
         cal_shape = (-1, 1)
-    elif graph_node_output.shape is not None and len(graph_node_output.shape) == 2 and axis == input_tensor_rank - 1:
-        cal_shape = (1, -1)
+    elif graph_node_output.shape is not None \
+        and len(graph_node_output.shape) == 2 \
+        and axis == input_tensor_rank - 1 \
+        and not isinstance(graph_node_output.shape[0], str):
+        cal_shape = (graph_node_output.shape[0], -1)
+    elif graph_node_output.shape is not None \
+        and len(graph_node_output.shape) == 2 \
+        and axis == input_tensor_rank - 1 \
+        and isinstance(graph_node_output.shape[0], str):
+        try:
+            dim_prod = int(np.prod(graph_node_output.shape[1:]))
+            cal_shape = (-1, dim_prod)
+        except:
+            cal_shape = (1, -1)
     elif input_tensor_rank >= 2 \
         and input_tensor_shape[0] is None \
         and len([idx for idx in input_tensor_shape[1:] if idx is not None]) == input_tensor_rank - 1 \

{onnx2tf-1.25.8 → onnx2tf-1.25.10}/onnx2tf/utils/common_functions.py

@@ -5202,7 +5202,19 @@ def merge_two_consecutive_identical_ops_into_one(
                 tf_type = tf.math.divide
 
     elif tf_func == 'Sub':
-        if (
+        if isinstance(input_tensor_1, np.ndarray) or hasattr(input_tensor_1, 'numpy'):
+            tf_layers_dict[graph_node_output.name]['tf_node'] = \
+                tf.math.subtract(
+                    x=input_tensor_1 \
+                        if not isinstance(input_tensor_1, np.ndarray) \
+                            else tf.convert_to_tensor(input_tensor_1),
+                    y=input_tensor_2 \
+                        if not isinstance(input_tensor_2, np.ndarray) \
+                            else tf.convert_to_tensor(input_tensor_2),
+                    name=graph_node.name,
+                )
+            tf_type = tf.math.subtract
+        elif (
             not isinstance(graph_node_input_1, np.ndarray) \
                 and 'merge_sub' in tf_layers_dict[graph_node_input_1.name] \
                 and tf_layers_dict[graph_node_input_1.name]['merge_sub']
@@ -5411,12 +5423,7 @@ def merge_two_consecutive_identical_ops_into_one(
                         elif next_graph_node_o_op == 'Sub':
                             # 8. `Add` -> `Sub` to `Single-Add`  : `10 + 5 - 8 -> 10 - 3`
                             if isinstance(next_graph_node_input_1, np.ndarray) or hasattr(next_graph_node_input_1, 'numpy'):
-                                if isinstance(input_tensor_1, np.ndarray) or hasattr(input_tensor_1, 'numpy'):
-                                    input_tensor_1 = (input_tensor_1 - next_graph_node_input_1)
-                                elif isinstance(input_tensor_2, np.ndarray) or hasattr(input_tensor_2, 'numpy'):
-                                    input_tensor_2 = (input_tensor_2 - next_graph_node_input_1)
-                                tf_layers_dict[graph_node_output.name]['merge_add'] = True
-                                tf_type = tf.identity
+                                tf_type = tf.math.add
                             elif isinstance(next_graph_node_input_2, np.ndarray) or hasattr(next_graph_node_input_2, 'numpy'):
                                 if isinstance(input_tensor_1, np.ndarray) or hasattr(input_tensor_1, 'numpy'):
                                     input_tensor_1 = (input_tensor_1 - next_graph_node_input_2)

{onnx2tf-1.25.8 → onnx2tf-1.25.10/onnx2tf.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: onnx2tf
-Version: 1.25.8
+Version: 1.25.10
 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:1.25.8
+  ghcr.io/pinto0309/onnx2tf:1.25.10
 
   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:1.25.8
+  docker.io/pinto0309/onnx2tf:1.25.10
 
   or