onnx2tf 1.29.22__py3-none-any.whl → 1.29.23__py3-none-any.whl

onnx2tf/__init__.py

@@ -1,3 +1,3 @@
 from onnx2tf.onnx2tf import convert, main
 
-__version__ = '1.29.22'
+__version__ = '1.29.23'

onnx2tf/ops/PRelu.py

@@ -124,22 +124,55 @@ def make_node(
         tf_layers_dict[graph_node_output.name].pop('nhwc')
 
     # Generation of TF OP
-    if replace_prelu_to_pseudo_prelu:
-        pos = tf.nn.relu(input_tensor)
-        neg = (input_tensor - abs(input_tensor)) * (slope * 0.5)
-        tf_layers_dict[graph_node_output.name]['tf_node'] = pos + neg
-    else:
+    shared_axes = None
+    input_shape = input_tensor.shape
+    slope_shape = slope.shape if hasattr(slope, 'shape') else None
+    if input_shape is not None and slope_shape is not None:
+        input_rank = len(input_shape)
+        if len(slope_shape) == input_rank - 1:
+            shared_axes = [
+                i + 1 for i, dim in enumerate(slope_shape)
+                if dim is not None and dim == 1
+            ]
+        elif len(slope_shape) == 1 and input_rank >= 3:
+            slope_dim = slope_shape[0]
+            channel_axis = None
+            if isinstance(slope_dim, int):
+                if input_shape[1] == slope_dim:
+                    channel_axis = 1
+                elif input_shape[-1] == slope_dim:
+                    channel_axis = input_rank - 1
+            if channel_axis is not None:
+                shared_axes = [ax for ax in range(1, input_rank) if ax != channel_axis]
+
+    if shared_axes is None:
         if slope.shape is not None \
             and len(slope.shape) > 0 \
             and sum([1 if dim is not None and dim == 1 else 0 for dim in slope.shape]) == len(slope.shape):
             shared_axes = [val + 1 for val in range(len(input_tensor.shape) - 1)]
         else:
-            shared_axes = [val + 1 for val in range(len(input_tensor.shape) - 2)]
-        tf_layers_dict[graph_node_output.name]['tf_node'] = \
-            PReLU(
-                weights=slope,
-                shared_axes=shared_axes,
-            )(input_tensor)
+            input_nhwc = tf_layers_dict.get(graph_node_output.name, {}).get('nhwc', False)
+            if input_nhwc:
+                shared_axes = [val + 1 for val in range(len(input_tensor.shape) - 2)]
+            else:
+                shared_axes = [val + 2 for val in range(len(input_tensor.shape) - 2)]
+
+    use_native_prelu = not replace_prelu_to_pseudo_prelu
+    if not use_native_prelu:
+        pos = tf.nn.relu(input_tensor)
+        neg = (input_tensor - abs(input_tensor)) * (slope * 0.5)
+        tf_layers_dict[graph_node_output.name]['tf_node'] = pos + neg
+    else:
+        try:
+            tf_layers_dict[graph_node_output.name]['tf_node'] = \
+                PReLU(
+                    weights=slope,
+                    shared_axes=shared_axes,
+                )(input_tensor)
+        except Exception:
+            pos = tf.nn.relu(input_tensor)
+            neg = (input_tensor - abs(input_tensor)) * (slope * 0.5)
+            tf_layers_dict[graph_node_output.name]['tf_node'] = pos + neg
 
     # Post-process transpose
     before_trans_shape = tf_layers_dict[graph_node_output.name]['tf_node'].shape

{onnx2tf-1.29.22.dist-info → onnx2tf-1.29.23.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: onnx2tf
-Version: 1.29.22
+Version: 1.29.23
 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
@@ -365,7 +365,7 @@ Video speed is adjusted approximately 50 times slower than actual speed.
   docker run --rm -it \
   -v `pwd`:/workdir \
   -w /workdir \
-  ghcr.io/pinto0309/onnx2tf:1.29.22
+  ghcr.io/pinto0309/onnx2tf:1.29.23
 
   or
 
@@ -373,7 +373,7 @@ Video speed is adjusted approximately 50 times slower than actual speed.
   docker run --rm -it \
   -v `pwd`:/workdir \
   -w /workdir \
-  docker.io/pinto0309/onnx2tf:1.29.22
+  docker.io/pinto0309/onnx2tf:1.29.23
 
   or
 
@@ -493,13 +493,20 @@ onnx2tf -i resnet18-v1-7.onnx -v info
 # without input OP name.
 # Note that if there are multiple input OPs, the zero dimension of all input OPs is
 # forced to be rewritten.
-# The `-ois` option allows undefined dimensions in all dimensions, including
-# the zero dimensionality, to be overwritten to a static shape, but requires
+# The `-sh/--shape-hints` option provides shape hints for input tensors with undefined
+# dimensions, significantly improving the conversion success rate for models with dynamic
+# input shapes. Specifying this option in combination with the `-b` option will further
+# improve the success rate of model conversion. The `-sh` option does not change ONNX
+# input OPs to static shapes.
+# The `-ois/--overwrite_input_shape` option allows undefined dimensions in all dimensions,
+# including the zero dimensionality, to be overwritten to a static shape, but requires
 # the input OP name to be specified.
 # e.g. -ois data1:1,3,224,224 data2:1,255 data3:1,224,6
 wget https://github.com/PINTO0309/onnx2tf/releases/download/0.0.2/resnet18-v1-7.onnx
 onnx2tf -i resnet18-v1-7.onnx -b 1
 or
+onnx2tf -i resnet18-v1-7.onnx -sh data:1,3,224,224 -b 1
+or
 onnx2tf -i resnet18-v1-7.onnx -ois data:1,3,224,224
 
 # Suppress automatic transposition of input OPs from NCW, NCHW, NCDHW to NWC, NHWC, NDHWC.

{onnx2tf-1.29.22.dist-info → onnx2tf-1.29.23.dist-info}/RECORD

@@ -1,4 +1,4 @@
-onnx2tf/__init__.py,sha256=EUJwryuQmTqI1Huqr9hrm1fJwxQqmGxUjAFgGvuB950,67
+onnx2tf/__init__.py,sha256=UHUGx_MsU6r_wJE0gjKBbArcku-dgsuNhDOnc8lkSn0,67
 onnx2tf/__main__.py,sha256=2RSCQ7d4lc6CwD-rlGn9UicPFg-P5du7ZD_yh-kuBEU,57
 onnx2tf/onnx2tf.py,sha256=BC-BFMf8QUG7PtOvpwglhe1sc4FhTO8AMrdlxKUN5jc,208204
 onnx2tf/ops/Abs.py,sha256=V7btmCG_ZvK_qJovUsguq0ZMJ349mhNQ4FHSgzP_Yuo,4029
@@ -118,7 +118,7 @@ onnx2tf/ops/OneHot.py,sha256=OThLm1MF1X75zx7gep_qdnRHsTRZX_tqZxjt6pAVi7E,6489
 onnx2tf/ops/OptionalGetElement.py,sha256=Qg8Lix1_rdGtVWC-UNC91ekx3ztB-5_UtWkg67M2Z5E,3031
 onnx2tf/ops/OptionalHasElement.py,sha256=fyZMPBWvLVohsm8J5FLMlYGBDr6HVq5lh9jL-yKp-tk,3031
 onnx2tf/ops/Or.py,sha256=7gyUSgbEVVQBp2t3G93pZlHNn0ejJfZ3rbSDOnFgUi0,4586
-onnx2tf/ops/PRelu.py,sha256=pHbsffhb2rLZPPb9NdKUT4f5-lC0TXmbZVafookXo90,6314
+onnx2tf/ops/PRelu.py,sha256=DxLBUgxQdO5IL1--xA5lbGq7dI-kr8UKn2Mf-4j8L5Q,7769
 onnx2tf/ops/Pad.py,sha256=xZOkZK-53sXU-d0nADAjR1wOpKqfzHeJjTmzwon6G4A,11883
 onnx2tf/ops/Pow.py,sha256=DZjrWQSyLw_BPXrKyoTqT9KJIxPfNxnYVcoTDBagDgM,7056
 onnx2tf/ops/QLinearAdd.py,sha256=OssQI0pd8KXdnCC8urCPKP8bpcvSX0D76bS7q4-xMSY,5027
@@ -211,7 +211,7 @@ 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-1.29.22.dist-info/WHEEL,sha256=fAguSjoiATBe7TNBkJwOjyL1Tt4wwiaQGtNtjRPNMQA,80
-onnx2tf-1.29.22.dist-info/entry_points.txt,sha256=GuhvLu7ZlYECumbmoiFlKX0mFPtFi_Ti9L-E5yuQqKs,42
-onnx2tf-1.29.22.dist-info/METADATA,sha256=eWX7J2epMkaxU8YW1paH77k23Lw7K4i_7WsJC9f6-is,156067
-onnx2tf-1.29.22.dist-info/RECORD,,
+onnx2tf-1.29.23.dist-info/WHEEL,sha256=fAguSjoiATBe7TNBkJwOjyL1Tt4wwiaQGtNtjRPNMQA,80
+onnx2tf-1.29.23.dist-info/entry_points.txt,sha256=GuhvLu7ZlYECumbmoiFlKX0mFPtFi_Ti9L-E5yuQqKs,42
+onnx2tf-1.29.23.dist-info/METADATA,sha256=ZMCERN7Q5orWmi94swf-4tt_Y3AkAI2em3tF_sQGR7g,156531
+onnx2tf-1.29.23.dist-info/RECORD,,