MLBEDSW-7997: [MLCE] Extended stride support for TRANSPOSE CONV

- Support for stride WxH 1x1
- Support for stride WxH 2x1 when IFM and KERNEL
  is 1D shape with height 1
- Added test to supported operators
- Updated SUPPORTED_OPS.md

Change-Id: Ic1abead8399a5e14a78d962f8aded0d3b3dbfcc4
Signed-off-by: Johan Alfven <johan.alfven@arm.com>X

4 files changed, 78 insertions, 17 deletions

diff --git a/SUPPORTED_OPS.md b/SUPPORTED_OPS.md
index 81ed6d1..0fef738 100644
--- a/SUPPORTED_OPS.md
+++ b/SUPPORTED_OPS.md
@@ -19,7 +19,7 @@ limitations under the License.
 # Supported Ops
 
 This file was automatically generated by Vela using the `--supported-ops-report` parameter.  
-Vela version: `3.9.0`
+Vela version: `3.9.1.dev2+gc02eaa3.d20230904`
 
 This file complies with
 [**Gitiles Markdown syntax**](https://github.com/google/gitiles/blob/master/Documentation/markdown.md)
@@ -408,7 +408,9 @@ This is a list of constraints that the TRANSPOSE_CONV operator must satisfy in o
 - Optional Bias tensor must be of shape: 1D
 - Optional Bias tensor must be of type: int32, int64
 - Optional Bias tensor values must fit within 40-bits
-- Stride values for both width and height must be 2
+- Stride values for width and height must match one of the following criteria:  
+        Stride values WxH must be 1x1 or 2x2  
+        Stride WxH 2x1 supported if ifm height and kernel height = 1
 - SAME padding: OFM dimensions must equal IFM dimensions multiplied by stride
 - VALID padding: OFM dimensions must equal IFM dimensions multiplied by stride,  
         minus difference between kernel size and stride
diff --git a/ethosu/vela/test/test_tflite_supported_operators.py b/ethosu/vela/test/test_tflite_supported_operators.py
index f54211f..e5cc280 100644
--- a/ethosu/vela/test/test_tflite_supported_operators.py
+++ b/ethosu/vela/test/test_tflite_supported_operators.py
@@ -218,12 +218,47 @@ def test_constraint_depth_multiplier():
 
 
 def test_constraint_tconv_stride():
-    # Strides must be 2
+    # Valid 2x2
     op = testutil.create_op_with_quant_tensors(Op.Conv2DBackpropInput, [0], [1, 2, 2, 1], weights_shape=[1, 1, 1, 1])
+    op.attrs = {"stride_w": 2, "stride_h": 2, "padding": Padding.SAME}
+    ifm = Tensor([1, 1, 1, 1], DataType.uint8, "ifm")
+    ifm.quantization = testutil.default_quant_params()
+    op.add_input_tensor(ifm)
+    assert support.is_operator_supported(op)
+    # Valid 1x1
+    op = testutil.create_op_with_quant_tensors(Op.Conv2DBackpropInput, [0], [1, 1, 1, 1], weights_shape=[1, 1, 1, 1])
     op.attrs = {"stride_w": 1, "stride_h": 1, "padding": Padding.SAME}
     ifm = Tensor([1, 1, 1, 1], DataType.uint8, "ifm")
     ifm.quantization = testutil.default_quant_params()
     op.add_input_tensor(ifm)
+    assert support.is_operator_supported(op)
+    # Valid 2x1 (WxH) ifm h and kernel h = 1
+    op = testutil.create_op_with_quant_tensors(Op.Conv2DBackpropInput, [0], [1, 1, 2, 1], weights_shape=[1, 1, 1, 1])
+    op.attrs = {"stride_w": 2, "stride_h": 1, "padding": Padding.SAME}
+    ifm = Tensor([1, 1, 1, 1], DataType.uint8, "ifm")
+    ifm.quantization = testutil.default_quant_params()
+    op.add_input_tensor(ifm)
+    assert support.is_operator_supported(op)
+    # Invalid 2x1 (WxH) ifm h = 2 and kernel h = 1
+    op = testutil.create_op_with_quant_tensors(Op.Conv2DBackpropInput, [0], [1, 1, 2, 1], weights_shape=[1, 1, 1, 1])
+    op.attrs = {"stride_w": 2, "stride_h": 1, "padding": Padding.SAME}
+    ifm = Tensor([1, 2, 1, 1], DataType.uint8, "ifm")
+    ifm.quantization = testutil.default_quant_params()
+    op.add_input_tensor(ifm)
+    assert not support.is_operator_supported(op)
+    # Invalid 2x1 (WxH) ifm h = 1 and kernel h = 2
+    op = testutil.create_op_with_quant_tensors(Op.Conv2DBackpropInput, [0], [1, 1, 1, 1], weights_shape=[1, 2, 1, 1])
+    op.attrs = {"stride_w": 2, "stride_h": 1, "padding": Padding.SAME}
+    ifm = Tensor([1, 2, 1, 1], DataType.uint8, "ifm")
+    ifm.quantization = testutil.default_quant_params()
+    op.add_input_tensor(ifm)
+    assert not support.is_operator_supported(op)
+    # Invalid 1x2 (WxH)
+    op = testutil.create_op_with_quant_tensors(Op.Conv2DBackpropInput, [0], [1, 1, 1, 1], weights_shape=[1, 1, 1, 1])
+    op.attrs = {"stride_w": 1, "stride_h": 2, "padding": Padding.SAME}
+    ifm = Tensor([1, 1, 1, 1], DataType.uint8, "ifm")
+    ifm.quantization = testutil.default_quant_params()
+    op.add_input_tensor(ifm)
     assert not support.is_operator_supported(op)
 
 
diff --git a/ethosu/vela/tflite_graph_optimiser.py b/ethosu/vela/tflite_graph_optimiser.py
index 9b98b8f..5107871 100644
--- a/ethosu/vela/tflite_graph_optimiser.py
+++ b/ethosu/vela/tflite_graph_optimiser.py
@@ -243,13 +243,15 @@ def calc_padding_and_skirt(padding_type, kernel, input_shape, explicit_padding):
     return padding, skirt
 
 
-def calc_upscaled_padding_and_skirt(padding_type, kernel_size, stride, input_shape, upscaling_factor):
+def calc_upscaled_padding_and_skirt(
+    padding_type, kernel_size, stride, input_shape, upscaling_factor_y, upscaling_factor_x
+):
     kernel_height, kernel_width = kernel_size[0], kernel_size[1]
     if padding_type == Padding.SAME:
-        ypad = needed_total_padding(int(input_shape.height) * upscaling_factor, int(stride[1]), int(kernel_height))
-        xpad = needed_total_padding(int(input_shape.width) * upscaling_factor, int(stride[2]), int(kernel_width))
-        right_pad = max(((xpad + 1) // upscaling_factor) - 1, 0)
-        bottom_pad = max(((ypad + 1) // upscaling_factor) - 1, 0)
+        ypad = needed_total_padding(int(input_shape.height) * upscaling_factor_y, int(stride[1]), int(kernel_height))
+        xpad = needed_total_padding(int(input_shape.width) * upscaling_factor_x, int(stride[2]), int(kernel_width))
+        right_pad = max(((xpad + 1) // upscaling_factor_x) - 1, 0)
+        bottom_pad = max(((ypad + 1) // upscaling_factor_y) - 1, 0)
         left_pad = max(kernel_width - 1 - right_pad, 0)
         top_pad = max(kernel_height - 1 - bottom_pad, 0)
     elif padding_type == Padding.VALID:
@@ -269,7 +271,11 @@ def fixup_conv2d_backprop(op: Operation, arch, nng) -> Operation:
         # flip the inputs
         op.inputs[0], op.inputs[2] = op.inputs[2], op.inputs[0]
         op.type = Op.Conv2DBackpropInputSwitchedBias
-        op.ifm_resampling_mode = resampling_mode.TRANSPOSE
+        stride_w = op.kernel.stride.x
+        stride_h = op.kernel.stride.y
+        if stride_w > 1 or stride_h > 1:
+            # Transpose conv2d with upscaling
+            op.ifm_resampling_mode = resampling_mode.TRANSPOSE
 
         # Update strides
         op.attrs.update({"stride_w": 1, "stride_h": 1, "strides": (1, 1, 1, 1)})
@@ -924,10 +930,15 @@ def add_padding_fields(op, arch, nng):
             else:
                 raise UnsupportedFeatureError(f"Unknown operation that uses padding: {optype_to_builtintype(op.type)}")
 
-            if op.type == Op.Conv2DBackpropInputSwitchedBias:
-                upscaling_factor = output_shape.height // input_shape.height
+            if op.type == Op.Conv2DBackpropInputSwitchedBias and op.ifm_resampling_mode == resampling_mode.TRANSPOSE:
+                # Transpose with upscale
                 padding, skirt = calc_upscaled_padding_and_skirt(
-                    op.attrs["padding"], kernel_size, op.attrs["strides"], input_shape, upscaling_factor
+                    op.attrs["padding"],
+                    kernel_size,
+                    op.attrs["strides"],
+                    input_shape,
+                    output_shape.height // input_shape.height,
+                    output_shape.width // input_shape.width,
                 )
             else:
                 padding, skirt = calc_padding_and_skirt(
diff --git a/ethosu/vela/tflite_supported_operators.py b/ethosu/vela/tflite_supported_operators.py
index 723c5f2..52b0485 100644
--- a/ethosu/vela/tflite_supported_operators.py
+++ b/ethosu/vela/tflite_supported_operators.py
@@ -590,11 +590,24 @@ class TFLiteSupportedOperators:
 
     @staticmethod
     def constraint_tconv_stride(op):
-        "Stride values for both width and height must be 2"
-        w = op.kernel.stride.x
-        h = op.kernel.stride.y
-        valid = (w == 2) and (h == 2)
-        return valid, f"Op has stride WxH as: {w}x{h}"
+        """Stride values for width and height must match one of the following criteria:
+        Stride values WxH must be 1x1 or 2x2
+        Stride WxH 2x1 supported if ifm height and kernel height = 1"""
+        s_w = op.kernel.stride.x
+        s_h = op.kernel.stride.y
+        k_h = op.kernel.height
+        i_h = op.ifm.shape[1]
+        valid = False
+        if s_w == 1 and s_h == 1:
+            valid = True
+
+        if s_w == 2 and s_h == 2:
+            valid = True
+
+        if s_w == 2 and s_h == 1 and i_h == 1 and k_h == 1:
+            valid = True
+
+        return valid, f"Op has ifm_height={i_h}, kernel_height={k_h} and stride WxH as {s_w}x{s_h}"
 
     @staticmethod
     def constraint_tconv_same(op):