merge a few PRs for 1.6.2

Author: guschmue

README.md

@@ -2,16 +2,16 @@
 
 | Build Type | OS | Python | Tensorflow | Onnx opset | Status |
 | ---        | ---    | ---    | ---        | ---        | ---    |
-| Unit Test - Basic | Linux, MacOS<sup>\*</sup>, Windows<sup>\*</sup> | 3.6, 3.7 | 1.12-1.15, 2.1 | 7-11 | [![Build Status](https://dev.azure.com/tensorflow-onnx/tensorflow-onnx/_apis/build/status/unit_test?branchName=master)](https://dev.azure.com/tensorflow-onnx/tensorflow-onnx/_build/latest?definitionId=16&branchName=master) |
-| Unit Test - Full | Linux, MacOS, Windows | 3.6, 3.7 | 1.12-1.15, 2.1 | 7-11 | [![Build Status](https://dev.azure.com/tensorflow-onnx/tensorflow-onnx/_apis/build/status/unit_test-matrix?branchName=master)](https://dev.azure.com/tensorflow-onnx/tensorflow-onnx/_build/latest?definitionId=18&branchName=master) | |
+| Unit Test - Basic | Linux, MacOS<sup>\*</sup>, Windows<sup>\*</sup> | 3.6, 3.7 | 1.12-1.15, 2.1-2.2 | 7-12 | [![Build Status](https://dev.azure.com/tensorflow-onnx/tensorflow-onnx/_apis/build/status/unit_test?branchName=master)](https://dev.azure.com/tensorflow-onnx/tensorflow-onnx/_build/latest?definitionId=16&branchName=master) |
+| Unit Test - Full | Linux, MacOS, Windows | 3.6, 3.7 | 1.12-1.15, 2.1-2.2 | 7-12 | [![Build Status](https://dev.azure.com/tensorflow-onnx/tensorflow-onnx/_apis/build/status/unit_test-matrix?branchName=master)](https://dev.azure.com/tensorflow-onnx/tensorflow-onnx/_build/latest?definitionId=18&branchName=master) | |
 
 ## Supported Versions
 
 ### ONNX
 
 tensorflow-onnx will use the ONNX version installed on your system and installs the latest ONNX version if none is found.
 
-We support opset 6 to 11. By default we use opset 8 for the resulting ONNX graph since most runtimes will support opset 8.
+We support ONNX opset-6 to opset-12. By default we use opset-8 for the resulting ONNX graph since most runtimes will support opset-8.
 Support for future opsets add added as they are released.
 
 If you want the graph to be generated with a specific opset, use ```--opset``` in the command line, for example ```--opset 11```.
@@ -20,13 +20,14 @@ If you want the graph to be generated with a specific opset, use ```--opset``` i
 
 We support all ```tf-1.x graphs```. To keep our test matrix manageable we test tf2onnx running on top of ```tf-1.12 and up```. tf2onnx-1.5.4 was the last version that was tested all the way back to tf-1.4.
 
-There is now ```experimental support for tf-2.x```. Basic unit tests are passing as well as control flow.
+There is now ```experimental support for tf-2.x```. 
+With the exception of LSTM unit tests, all unit tests are enabled and passing.
 Unit tests that we still need to fix are marked with ```@skip_tf2```.
 GRU/LSTM's are converting but not runnable due to type/shape inference issues at runtime (working on that one).
-All unit tests are running in eager mode and after execution we take the python function, make it a graph and convert this to onnx.
-If running under tf-2.x we are using the tensorflow V2 controlflow.
+All unit tests are running in eager mode. After execution we take the python function, make it a graph and convert it to ONNX.
+When running under tf-2.x tf2onnx will use the tensorflow V2 controlflow.
 
-You can install tf2onnx on top of tf-1.x or tf-2.x and convert tf-1.x or tf-2.x models.
+You can install tf2onnx on top of tf-1.x or tf-2.x.
 
 ### Python
 

VERSION_NUMBER

@@ -1 +1 @@
-1.6.1
+1.6.2

tf2onnx/graph.py

@@ -301,7 +301,7 @@ def set_tensor_value(self, new_val):
         self.set_attr("value", onnx_tensor)
         # track shapes in _output_shapes
         self._graph_check()
-        self.graph.set_shape(onnx_tensor.name, onnx_tensor.dims)
+        self.graph.set_shape(onnx_tensor.name, list(onnx_tensor.dims))
 
     def get_body_graphs(self):
         self._graph_check()
@@ -484,6 +484,14 @@ def inputs(self):
                 all_inputs.append(n)
         return all_inputs
 
+    def make_consts(self, values, np_type=np.int64, skip_conversion=False, raw=True):
+        """create list of consts of same type"""
+        consts = []
+        for value in values:
+            np_val = np.array(value).astype(np_type)
+            consts.append(self.make_const(utils.make_name("const"), np_val, skip_conversion, raw))
+        return consts
+
     def make_const(self, name, np_val, skip_conversion=False, raw=True):
         """Make a new constant in the graph.
         Args:

tf2onnx/onnx_opset/generator.py

@@ -194,3 +194,15 @@ def version_8(cls, ctx, node, **kwargs):
         ctx.remove_node(node.name)
         ctx.add_graph_input(output_names[0], type_0, shape_0)
         ctx.add_graph_input(output_names[1], type_1, shape_1)
+
+
+@tf_op("QueueDequeueManyV2")
+class QueueDequeueManyV2:
+    @classmethod
+    def version_8(cls, ctx, node, **kwargs):
+        outputs = node.output
+        shapes = node.output_shapes
+        dtypes = node.output_dtypes
+        ctx.remove_node(node.name)
+        for i, output in enumerate(outputs):
+            ctx.add_graph_input(output, dtypes[i], shapes[i])

tf2onnx/onnx_opset/nn.py

@@ -248,6 +248,7 @@ def version_1(cls, ctx, node, **kwargs):
         # Note: inputs are reversed from what one would expect.
         conv_kernel_shape(ctx, node, 1)
         input_shape = ctx.get_shape(node.input[2])
+        output_shape_orig = node.output_shapes
 
         # ouput_shape is explicitly specified here, in this case pads values are auto generated/calculated.
         if node.inputs[0].is_const():
@@ -285,7 +286,8 @@ def version_1(cls, ctx, node, **kwargs):
             const_one_two = ctx.make_const(utils.make_name(node.name + "_const_one_two"),
                                            np.array([1, 2], dtype=np.int64))
             slice_node = ctx.make_node("Slice",
-                                       [node.output[0], starts.output[0], ends.output[0], const_one_two.output[0]])
+                                       [node.output[0], starts.output[0], ends.output[0], const_one_two.output[0]],
+                                       shapes=output_shape_orig)
             downstream_nodes = ctx.find_output_consumers(node.output[0])
             downstream_nodes.remove(output_shape)
             downstream_nodes.remove(slice_node)