onnx2tf 1.29.11__py3-none-any.whl → 1.29.12__py3-none-any.whl

onnx2tf/__init__.py

@@ -1,3 +1,3 @@
 from onnx2tf.onnx2tf import convert, main
 
-__version__ = '1.29.11'
+__version__ = '1.29.12'

onnx2tf/ops/MatMul.py

@@ -444,19 +444,68 @@ def make_node(
         onnx_output_shape = [
             dim if not isinstance(dim, str) else None for dim in onnx_output_shape
         ]
+
+        def _shape_match(a_shape, b_shape):
+            if len(a_shape) != len(b_shape):
+                return False
+            for a_dim, b_dim in zip(a_shape, b_shape):
+                if a_dim is None or b_dim is None:
+                    continue
+                if a_dim != b_dim:
+                    return False
+            return True
+
+        # Squeeze unit dims if ONNX output rank is smaller.
+        if len(post_matmul_shape) > len(onnx_output_shape):
+            squeeze_axes = []
+            tmp_shape = list(post_matmul_shape)
+            while len(tmp_shape) > len(onnx_output_shape) and tmp_shape[-1] == 1:
+                squeeze_axes.append(len(tmp_shape) - 1)
+                tmp_shape.pop()
+            if squeeze_axes and len(tmp_shape) == len(onnx_output_shape) \
+                and _shape_match(tmp_shape, onnx_output_shape):
+                tf_layers_dict[graph_node_output.name]['tf_node'] = \
+                    tf.squeeze(
+                        input=tf_layers_dict[graph_node_output.name]['tf_node'],
+                        axis=squeeze_axes,
+                    )
+                post_matmul_shape = list(tf_layers_dict[graph_node_output.name]['tf_node'].shape)
+                post_matmul_shape_none_count = sum(
+                    [1 if dim is None else 0 for dim in post_matmul_shape]
+                )
+            else:
+                leading_ones = 0
+                tmp_shape = list(post_matmul_shape)
+                while len(tmp_shape) > len(onnx_output_shape) and tmp_shape and tmp_shape[0] == 1:
+                    leading_ones += 1
+                    tmp_shape.pop(0)
+                if leading_ones and len(tmp_shape) == len(onnx_output_shape) \
+                    and _shape_match(tmp_shape, onnx_output_shape):
+                    tf_layers_dict[graph_node_output.name]['tf_node'] = \
+                        tf.squeeze(
+                            input=tf_layers_dict[graph_node_output.name]['tf_node'],
+                            axis=list(range(leading_ones)),
+                        )
+                    post_matmul_shape = list(tf_layers_dict[graph_node_output.name]['tf_node'].shape)
+                    post_matmul_shape_none_count = sum(
+                        [1 if dim is None else 0 for dim in post_matmul_shape]
+                    )
+
         onnx_output_shape_none_count = sum([1 if dim is None else 0 for dim in onnx_output_shape])
-        if post_matmul_shape_none_count == onnx_output_shape_none_count:
+        if post_matmul_shape_none_count == onnx_output_shape_none_count \
+            and post_matmul_shape != list(onnx_output_shape):
             post_transpose_perm = []
             for dim in onnx_output_shape:
                 idx = post_matmul_shape.index(dim)
                 post_transpose_perm.append(idx)
                 post_matmul_shape[idx] = -999
 
-            tf_layers_dict[graph_node_output.name]['tf_node'] = \
-                tf.transpose(
-                    a=tf_layers_dict[graph_node_output.name]['tf_node'],
-                    perm=post_transpose_perm,
-                )
+            if len(post_transpose_perm) == len(post_matmul_shape):
+                tf_layers_dict[graph_node_output.name]['tf_node'] = \
+                    tf.transpose(
+                        a=tf_layers_dict[graph_node_output.name]['tf_node'],
+                        perm=post_transpose_perm,
+                    )
 
     # Post-process transpose
     tf_layers_dict[graph_node_output.name]['tf_node'] = post_process_transpose(

{onnx2tf-1.29.11.dist-info → onnx2tf-1.29.12.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: onnx2tf
-Version: 1.29.11
+Version: 1.29.12
 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).
 Keywords: onnx,tensorflow,tflite,keras,deep-learning,machine-learning
 Author: Katsuya Hyodo
@@ -363,7 +363,7 @@ Video speed is adjusted approximately 50 times slower than actual speed.
   docker run --rm -it \
   -v `pwd`:/workdir \
   -w /workdir \
-  ghcr.io/pinto0309/onnx2tf:1.29.11
+  ghcr.io/pinto0309/onnx2tf:1.29.12
 
   or
 
@@ -371,7 +371,7 @@ Video speed is adjusted approximately 50 times slower than actual speed.
   docker run --rm -it \
   -v `pwd`:/workdir \
   -w /workdir \
-  docker.io/pinto0309/onnx2tf:1.29.11
+  docker.io/pinto0309/onnx2tf:1.29.12
 
   or
 

{onnx2tf-1.29.11.dist-info → onnx2tf-1.29.12.dist-info}/RECORD

@@ -1,4 +1,4 @@
-onnx2tf/__init__.py,sha256=YcIMmqFje14SgZxYSfLRHbInf0F8cWXJjfwWrwz2mxg,67
+onnx2tf/__init__.py,sha256=89EgFjqomm_s1GTO1Is-NN_4IBNeGFXu31Zcmotmbes,67
 onnx2tf/__main__.py,sha256=2RSCQ7d4lc6CwD-rlGn9UicPFg-P5du7ZD_yh-kuBEU,57
 onnx2tf/onnx2tf.py,sha256=yR8aKaEn01Q8dEeYDqHIsuZuG6l5TGQniHDlPiUROx4,152238
 onnx2tf/ops/Abs.py,sha256=V7btmCG_ZvK_qJovUsguq0ZMJ349mhNQ4FHSgzP_Yuo,4029
@@ -92,7 +92,7 @@ onnx2tf/ops/LogSoftmax.py,sha256=j2nhYY7__8ViLFJVLA5tS98QEvGS1gTIW0QCdnZWUPQ,392
 onnx2tf/ops/Loop.py,sha256=I32CWoex8FMXm9KE2aomADB4jK5BzaMoAKvtPnBJy6A,14593
 onnx2tf/ops/LpNormalization.py,sha256=Uu15HgxFNXb6gNMgdTJyf0SLPaLbcbkOYqY_4hMBxNA,3153
 onnx2tf/ops/LpPool.py,sha256=96eI1FaDgW0M_USWBCHFedvtojHTLL28_lb3mcEV55A,10470
-onnx2tf/ops/MatMul.py,sha256=KHhRyQCyxe6845f-AOI1UJzA3rGTssG6eyKmDw0oegs,21466
+onnx2tf/ops/MatMul.py,sha256=X9cQSD4BCogkDP6D4YZEZmOWnsceGL8ppN8E4kqyjB0,23926
 onnx2tf/ops/MatMulInteger.py,sha256=qHqzdJNI9SeJDbW8pR90baYCdGN6FdOez4hi9EzwXoc,6538
 onnx2tf/ops/Max.py,sha256=w5nMciO_6ApYUobHuwMGuS3xhuza7eSvKDRhvMPgAuo,3256
 onnx2tf/ops/MaxPool.py,sha256=_JC4eqBTh-qLkZCMG8RZhthRZ8D2d821zaFMWeGMEWc,15775
@@ -199,7 +199,7 @@ onnx2tf/utils/enums.py,sha256=7c5TqetqB07VjyHoxJHfLgtqBqk9ZRyUF33fPOJR1IM,1649
 onnx2tf/utils/iterative_json_optimizer.py,sha256=qqeIxWGxrhcCYk8-ebWnblnOkzDCwi-nseipHzHR_bk,10436
 onnx2tf/utils/json_auto_generator.py,sha256=OC-SfKtUg7zUxaXTAg6kT0ShzIc3ByjDa3FNp173DtA,60302
 onnx2tf/utils/logging.py,sha256=yUCmPuJ_XiUItM3sZMcaMO24JErkQy7zZwVTYWAuiKg,1982
-onnx2tf-1.29.11.dist-info/WHEEL,sha256=e_m4S054HL0hyR3CpOk-b7Q7fDX6BuFkgL5OjAExXas,80
-onnx2tf-1.29.11.dist-info/entry_points.txt,sha256=GuhvLu7ZlYECumbmoiFlKX0mFPtFi_Ti9L-E5yuQqKs,42
-onnx2tf-1.29.11.dist-info/METADATA,sha256=jeSTHVzVOoEkFVfyO6OVFniy_mrUfZKW9Gez1RYMkVM,154193
-onnx2tf-1.29.11.dist-info/RECORD,,
+onnx2tf-1.29.12.dist-info/WHEEL,sha256=e_m4S054HL0hyR3CpOk-b7Q7fDX6BuFkgL5OjAExXas,80
+onnx2tf-1.29.12.dist-info/entry_points.txt,sha256=GuhvLu7ZlYECumbmoiFlKX0mFPtFi_Ti9L-E5yuQqKs,42
+onnx2tf-1.29.12.dist-info/METADATA,sha256=Ddf7-_nYlEjEOlH3taykx6G5ULbARSgF7cuFlj7HD_0,154193
+onnx2tf-1.29.12.dist-info/RECORD,,