onnx2tf 1.29.17__tar.gz → 1.29.18__tar.gz

{onnx2tf-1.29.17 → onnx2tf-1.29.18}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: onnx2tf
-Version: 1.29.17
+Version: 1.29.18
 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
@@ -175,7 +175,7 @@ https://github.com/PINTO0309/onnx2tf/wiki/model_status
   |HardSwish|:heavy_check_mark:|
   |Identity|:heavy_check_mark:|
   |If|:heavy_check_mark:|
-  |ImageDecoder|**Help wanted**|
+  |ImageDecoder|:white_check_mark:|
   |Input|:heavy_check_mark:|
   |InstanceNormalization|:heavy_check_mark:|
   |Inverse|:heavy_check_mark:|
@@ -207,7 +207,7 @@ https://github.com/PINTO0309/onnx2tf/wiki/model_status
   |Mul|:heavy_check_mark:|
   |Multinomial|:heavy_check_mark:|
   |Neg|:heavy_check_mark:|
-  |NegativeLogLikelihoodLoss|**Help wanted**|
+  |NegativeLogLikelihoodLoss|:heavy_check_mark:|
   |NonMaxSuppression|:heavy_check_mark:|
   |NonZero|:heavy_check_mark:|
   |Optional|**Help wanted**|
@@ -244,19 +244,20 @@ https://github.com/PINTO0309/onnx2tf/wiki/model_status
   |ReduceProd|:heavy_check_mark:|
   |ReduceSum|:heavy_check_mark:|
   |ReduceSumSquare|:heavy_check_mark:|
+  |RegexFullMatch|:heavy_check_mark:|
   |Relu|:heavy_check_mark:|
   |Reshape|:heavy_check_mark:|
   |Resize|:heavy_check_mark:|
   |ReverseSequence|:heavy_check_mark:|
   |RNN|:heavy_check_mark:|
   |RoiAlign|:heavy_check_mark:|
-  |RotaryEmbedding|**Help wanted**|
+  |RotaryEmbedding|:heavy_check_mark:|
   |Round|:heavy_check_mark:|
   |ScaleAndTranslate|:heavy_check_mark:|
   |Scatter|:heavy_check_mark:|
   |ScatterElements|:heavy_check_mark:|
   |ScatterND|:heavy_check_mark:|
-  |Scan|**Help wanted**|
+  |Scan|:heavy_check_mark:|
   |Selu|:heavy_check_mark:|
   |SequenceAt|:heavy_check_mark:|
   |SequenceConstruct|:heavy_check_mark:|
@@ -273,7 +274,7 @@ https://github.com/PINTO0309/onnx2tf/wiki/model_status
   |Size|:heavy_check_mark:|
   |Slice|:heavy_check_mark:|
   |Softmax|:heavy_check_mark:|
-  |SoftmaxCrossEntropyLoss|**Help wanted**|
+  |SoftmaxCrossEntropyLoss|:heavy_check_mark:|
   |Softplus|:heavy_check_mark:|
   |Softsign|:heavy_check_mark:|
   |SpaceToDepth|:heavy_check_mark:|
@@ -282,14 +283,14 @@ https://github.com/PINTO0309/onnx2tf/wiki/model_status
   |Sqrt|:heavy_check_mark:|
   |Squeeze|:heavy_check_mark:|
   |STFT|:white_check_mark:|
-  |StringConcat|**Help wanted**|
-  |StringNormalizer|:white_check_mark:|
-  |StringSplit|**Help wanted**|
+  |StringConcat|:heavy_check_mark:|
+  |StringNormalizer|:heavy_check_mark:|
+  |StringSplit|:heavy_check_mark:|
   |Sub|:heavy_check_mark:|
   |Sum|:heavy_check_mark:|
   |Tan|:heavy_check_mark:|
   |Tanh|:heavy_check_mark:|
-  |TensorScatter|**Help wanted**|
+  |TensorScatter|:heavy_check_mark:|
   |TfIdfVectorizer|**Help wanted**|
   |ThresholdedRelu|:heavy_check_mark:|
   |Tile|:heavy_check_mark:|
@@ -364,7 +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:1.29.17
+  ghcr.io/pinto0309/onnx2tf:1.29.18
 
   or
 
@@ -372,7 +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:1.29.17
+  docker.io/pinto0309/onnx2tf:1.29.18
 
   or
 

{onnx2tf-1.29.17 → onnx2tf-1.29.18}/README.md

@@ -133,7 +133,7 @@ https://github.com/PINTO0309/onnx2tf/wiki/model_status
   |HardSwish|:heavy_check_mark:|
   |Identity|:heavy_check_mark:|
   |If|:heavy_check_mark:|
-  |ImageDecoder|**Help wanted**|
+  |ImageDecoder|:white_check_mark:|
   |Input|:heavy_check_mark:|
   |InstanceNormalization|:heavy_check_mark:|
   |Inverse|:heavy_check_mark:|
@@ -165,7 +165,7 @@ https://github.com/PINTO0309/onnx2tf/wiki/model_status
   |Mul|:heavy_check_mark:|
   |Multinomial|:heavy_check_mark:|
   |Neg|:heavy_check_mark:|
-  |NegativeLogLikelihoodLoss|**Help wanted**|
+  |NegativeLogLikelihoodLoss|:heavy_check_mark:|
   |NonMaxSuppression|:heavy_check_mark:|
   |NonZero|:heavy_check_mark:|
   |Optional|**Help wanted**|
@@ -202,19 +202,20 @@ https://github.com/PINTO0309/onnx2tf/wiki/model_status
   |ReduceProd|:heavy_check_mark:|
   |ReduceSum|:heavy_check_mark:|
   |ReduceSumSquare|:heavy_check_mark:|
+  |RegexFullMatch|:heavy_check_mark:|
   |Relu|:heavy_check_mark:|
   |Reshape|:heavy_check_mark:|
   |Resize|:heavy_check_mark:|
   |ReverseSequence|:heavy_check_mark:|
   |RNN|:heavy_check_mark:|
   |RoiAlign|:heavy_check_mark:|
-  |RotaryEmbedding|**Help wanted**|
+  |RotaryEmbedding|:heavy_check_mark:|
   |Round|:heavy_check_mark:|
   |ScaleAndTranslate|:heavy_check_mark:|
   |Scatter|:heavy_check_mark:|
   |ScatterElements|:heavy_check_mark:|
   |ScatterND|:heavy_check_mark:|
-  |Scan|**Help wanted**|
+  |Scan|:heavy_check_mark:|
   |Selu|:heavy_check_mark:|
   |SequenceAt|:heavy_check_mark:|
   |SequenceConstruct|:heavy_check_mark:|
@@ -231,7 +232,7 @@ https://github.com/PINTO0309/onnx2tf/wiki/model_status
   |Size|:heavy_check_mark:|
   |Slice|:heavy_check_mark:|
   |Softmax|:heavy_check_mark:|
-  |SoftmaxCrossEntropyLoss|**Help wanted**|
+  |SoftmaxCrossEntropyLoss|:heavy_check_mark:|
   |Softplus|:heavy_check_mark:|
   |Softsign|:heavy_check_mark:|
   |SpaceToDepth|:heavy_check_mark:|
@@ -240,14 +241,14 @@ https://github.com/PINTO0309/onnx2tf/wiki/model_status
   |Sqrt|:heavy_check_mark:|
   |Squeeze|:heavy_check_mark:|
   |STFT|:white_check_mark:|
-  |StringConcat|**Help wanted**|
-  |StringNormalizer|:white_check_mark:|
-  |StringSplit|**Help wanted**|
+  |StringConcat|:heavy_check_mark:|
+  |StringNormalizer|:heavy_check_mark:|
+  |StringSplit|:heavy_check_mark:|
   |Sub|:heavy_check_mark:|
   |Sum|:heavy_check_mark:|
   |Tan|:heavy_check_mark:|
   |Tanh|:heavy_check_mark:|
-  |TensorScatter|**Help wanted**|
+  |TensorScatter|:heavy_check_mark:|
   |TfIdfVectorizer|**Help wanted**|
   |ThresholdedRelu|:heavy_check_mark:|
   |Tile|:heavy_check_mark:|
@@ -322,7 +323,7 @@ Video speed is adjusted approximately 50 times slower than actual speed.
   docker run --rm -it \
   -v `pwd`:/workdir \
   -w /workdir \
-  ghcr.io/pinto0309/onnx2tf:1.29.17
+  ghcr.io/pinto0309/onnx2tf:1.29.18
 
   or
 
@@ -330,7 +331,7 @@ Video speed is adjusted approximately 50 times slower than actual speed.
   docker run --rm -it \
   -v `pwd`:/workdir \
   -w /workdir \
-  docker.io/pinto0309/onnx2tf:1.29.17
+  docker.io/pinto0309/onnx2tf:1.29.18
 
   or
 

{onnx2tf-1.29.17 → onnx2tf-1.29.18}/onnx2tf/__init__.py

@@ -1,3 +1,3 @@
 from onnx2tf.onnx2tf import convert, main
 
-__version__ = '1.29.17'
+__version__ = '1.29.18'

onnx2tf-1.29.18/onnx2tf/ops/ImageDecoder.py

@@ -0,0 +1,147 @@
+import random
+random.seed(0)
+import numpy as np
+np.random.seed(0)
+import tensorflow as tf
+import onnx_graphsurgeon as gs
+import cv2
+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,
+)
+from onnx2tf.utils.logging import *
+
+
+def _as_tensor(value):
+    if isinstance(value, np.ndarray):
+        return tf.convert_to_tensor(value)
+    if isinstance(value, (np.generic, int, float, bool, str, bytes)):
+        return tf.convert_to_tensor(value)
+    return value
+
+
+def _decode_image_np(encoded_stream, pixel_format):
+    if encoded_stream is None:
+        return np.zeros((0, 0, 0), dtype=np.uint8)
+    if encoded_stream.dtype != np.uint8:
+        encoded_stream = encoded_stream.astype(np.uint8)
+    if encoded_stream.size == 0:
+        return np.zeros((0, 0, 0), dtype=np.uint8)
+    if encoded_stream.ndim != 1:
+        encoded_stream = encoded_stream.reshape(-1)
+    try:
+        if pixel_format == 'Grayscale':
+            flag = cv2.IMREAD_GRAYSCALE
+        else:
+            flag = cv2.IMREAD_COLOR
+        decoded = cv2.imdecode(encoded_stream, flag)
+        if decoded is None:
+            raise ValueError('cv2.imdecode failed')
+        if pixel_format == 'RGB':
+            decoded = cv2.cvtColor(decoded, cv2.COLOR_BGR2RGB)
+        if pixel_format == 'Grayscale' and decoded.ndim == 2:
+            decoded = decoded[..., np.newaxis]
+        return decoded.astype(np.uint8)
+    except Exception:
+        if pixel_format == 'Grayscale':
+            return np.zeros((0, 0, 1), dtype=np.uint8)
+        return np.zeros((0, 0, 3), dtype=np.uint8)
+
+
+@print_node_info
+@inverted_operation_enable_disable
+@get_replacement_parameter
+def make_node(
+    *,
+    graph_node: gs.Node,
+    tf_layers_dict: dict,
+    **kwargs: dict,
+):
+    """ImageDecoder
+
+    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 = 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
+
+    input_tensor = tf_layers_dict[graph_node_input.name]['tf_node'] \
+        if isinstance(graph_node_input, gs.Variable) else graph_node_input
+
+    # Preserving Graph Structure (Dict)
+    tf_layers_dict[graph_node_output.name] = {
+        'optype': graph_node.op,
+        'shape': shape,
+        'dtype': dtype,
+    }
+
+    # Pre-process transpose
+    input_tensor = pre_process_transpose(
+        value_before_transpose=input_tensor,
+        param_target='inputs',
+        param_name=graph_node.inputs[0].name,
+        **kwargs,
+    )
+
+    # Generation of TF OP
+    input_tensor = _as_tensor(input_tensor)
+    pixel_format = graph_node.attrs.get('pixel_format', 'RGB')
+    if pixel_format not in ['RGB', 'BGR', 'Grayscale']:
+        error(
+            f'ImageDecoder pixel_format={pixel_format} is not supported.\n' +
+            f'graph_node.name: {graph_node.name}'
+        )
+        pixel_format = 'RGB'
+
+    decoded = tf.numpy_function(
+        func=lambda x: _decode_image_np(x, pixel_format),
+        inp=[input_tensor],
+        Tout=tf.uint8,
+        name=graph_node.name,
+    )
+    channels = 1 if pixel_format == 'Grayscale' else 3
+    decoded = tf.ensure_shape(decoded, [None, None, channels])
+    tf_layers_dict[graph_node_output.name]['tf_node'] = decoded
+
+    # 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': 'ImageDecoder',
+                'tf_inputs': {
+                    'encoded_stream': input_tensor,
+                    'pixel_format': pixel_format,
+                },
+                'tf_outputs': {
+                    'output': tf_layers_dict[graph_node_output.name]['tf_node'],
+                },
+            }
+        )

onnx2tf-1.29.18/onnx2tf/ops/NegativeLogLikelihoodLoss.py

@@ -0,0 +1,237 @@
+import sys
+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,
+    convert_axis,
+    print_node_info,
+    inverted_operation_enable_disable,
+    make_tf_node_info,
+    get_replacement_parameter,
+    pre_process_transpose,
+    post_process_transpose,
+)
+from onnx2tf.utils.enums import NUMPY_DTYPES_TO_TF_DTYPES
+from onnx2tf.utils.logging import *
+
+
+def _as_tensor(value):
+    if isinstance(value, np.ndarray):
+        return tf.convert_to_tensor(value)
+    if isinstance(value, (np.generic, int, float, bool, str, bytes)):
+        return tf.convert_to_tensor(value)
+    return value
+
+
+def _move_class_to_last(tensor, class_axis):
+    rank = tensor.shape.rank
+    if rank is None:
+        rank = tf.rank(tensor)
+    if isinstance(rank, int):
+        if class_axis == rank - 1:
+            return tensor, None
+        perm = [i for i in range(rank) if i != class_axis] + [class_axis]
+        return tf.transpose(tensor, perm=perm), perm
+    return tensor, None
+
+
+@print_node_info
+@inverted_operation_enable_disable
+@get_replacement_parameter
+def make_node(
+    *,
+    graph_node: gs.Node,
+    tf_layers_dict: dict,
+    **kwargs: dict,
+):
+    """NegativeLogLikelihoodLoss
+
+    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
+    if len(graph_node.inputs) >= 3:
+        before_op_output_shape_trans_3 = \
+            tf_layers_dict.get(graph_node.inputs[2].name, {}).get('before_op_output_shape_trans', True)
+        before_op_output_shape_trans = \
+            before_op_output_shape_trans \
+            and before_op_output_shape_trans_3
+
+    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_input_3 = None
+    if len(graph_node.inputs) >= 3:
+        graph_node_input_3 = get_constant_or_variable(
+            graph_node.inputs[2],
+            before_op_output_shape_trans,
+        )
+
+    graph_node_output: gs.Variable = graph_node.outputs[0]
+    shape = graph_node_output.shape
+    dtype = graph_node_output.dtype
+    output_tf_dtype = NUMPY_DTYPES_TO_TF_DTYPES[dtype] \
+        if isinstance(dtype, np.dtype) else dtype
+
+    input_tensor = tf_layers_dict[graph_node_input_1.name]['tf_node'] \
+        if isinstance(graph_node_input_1, gs.Variable) else graph_node_input_1
+    target_tensor = tf_layers_dict[graph_node_input_2.name]['tf_node'] \
+        if isinstance(graph_node_input_2, gs.Variable) else graph_node_input_2
+    weight_tensor = None
+    if graph_node_input_3 is not None:
+        weight_tensor = tf_layers_dict[graph_node_input_3.name]['tf_node'] \
+            if isinstance(graph_node_input_3, gs.Variable) else graph_node_input_3
+
+    reduction = graph_node.attrs.get('reduction', 'mean')
+    ignore_index = graph_node.attrs.get('ignore_index', None)
+
+    input_rank = len(input_tensor.shape)
+    class_axis = convert_axis(
+        axis=1,
+        tensor_rank=input_rank,
+        before_op_output_shape_trans=before_op_output_shape_trans,
+    )
+
+    # Preserving Graph Structure (Dict)
+    output_entry = {
+        'optype': graph_node.op,
+        'shape': shape,
+        'dtype': dtype,
+    }
+    if reduction == 'none':
+        output_entry['nhwc'] = tf_layers_dict[graph_node_input_1.name]['nhwc'] \
+            if isinstance(graph_node_input_1, gs.Variable) \
+                and 'nhwc' in tf_layers_dict[graph_node_input_1.name].keys() else False
+    tf_layers_dict[graph_node_output.name] = output_entry
+
+    # Pre-process transpose
+    input_tensor = pre_process_transpose(
+        value_before_transpose=input_tensor,
+        param_target='inputs',
+        param_name=graph_node.inputs[0].name,
+        **kwargs,
+    )
+    target_tensor = pre_process_transpose(
+        value_before_transpose=target_tensor,
+        param_target='inputs',
+        param_name=graph_node.inputs[1].name,
+        **kwargs,
+    )
+    if weight_tensor is not None:
+        weight_tensor = pre_process_transpose(
+            value_before_transpose=weight_tensor,
+            param_target='inputs',
+            param_name=graph_node.inputs[2].name,
+            **kwargs,
+        )
+
+    # Generation of TF OP
+    input_tensor = _as_tensor(input_tensor)
+    target_tensor = _as_tensor(target_tensor)
+    if weight_tensor is not None:
+        weight_tensor = _as_tensor(weight_tensor)
+
+    log_prob = input_tensor
+    log_prob, _ = _move_class_to_last(log_prob, class_axis)
+
+    depth = log_prob.shape[-1]
+    if depth is None:
+        depth = tf.shape(log_prob)[-1]
+    depth = tf.cast(depth, tf.int32)
+
+    labels = tf.cast(target_tensor, tf.int32)
+    if ignore_index is not None:
+        ignore_index_val = tf.cast(ignore_index, labels.dtype)
+        mask = tf.equal(labels, ignore_index_val)
+        labels_safe = tf.where(mask, tf.zeros_like(labels), labels)
+    else:
+        mask = None
+        labels_safe = labels
+
+    one_hot = tf.one_hot(
+        indices=labels_safe,
+        depth=depth,
+        axis=-1,
+        dtype=log_prob.dtype,
+    )
+    selected = tf.reduce_sum(log_prob * one_hot, axis=-1)
+    loss = -selected
+
+    weight_per_label = None
+    if weight_tensor is not None:
+        weight_per_label = tf.gather(weight_tensor, labels_safe)
+        weight_per_label = tf.cast(weight_per_label, loss.dtype)
+        if mask is not None:
+            weight_per_label = tf.where(mask, tf.zeros_like(weight_per_label), weight_per_label)
+        loss = loss * weight_per_label
+
+    if mask is not None:
+        loss = tf.where(mask, tf.zeros_like(loss), loss)
+
+    if reduction == 'none':
+        output_tensor = loss
+    elif reduction == 'sum':
+        output_tensor = tf.reduce_sum(loss)
+    elif reduction == 'mean':
+        if weight_per_label is None:
+            output_tensor = tf.reduce_mean(loss)
+        else:
+            denom = tf.reduce_sum(weight_per_label)
+            output_tensor = tf.math.divide_no_nan(tf.reduce_sum(loss), denom)
+    else:
+        error(
+            f'NegativeLogLikelihoodLoss reduction={reduction} is not supported.\n' +
+            f'graph_node.name: {graph_node.name}'
+        )
+        sys.exit(1)
+
+    if output_tf_dtype is not None and output_tensor.dtype != output_tf_dtype:
+        output_tensor = tf.cast(output_tensor, output_tf_dtype)
+
+    tf_layers_dict[graph_node_output.name]['tf_node'] = output_tensor
+
+    # 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': 'NegativeLogLikelihoodLoss',
+                'tf_inputs': {
+                    'input': input_tensor,
+                    'target': target_tensor,
+                    'weight': weight_tensor,
+                    'reduction': reduction,
+                    'ignore_index': ignore_index,
+                },
+                'tf_outputs': {
+                    'output': tf_layers_dict[graph_node_output.name]['tf_node'],
+                },
+            }
+        )