[GitHub] [incubator-tvm] comaniac commented on a change in pull request #5272: [BYOC] Add example of Composite + Annotate for DNNL fused op

[GitBox <gi...@apache.org>]

comaniac commented on a change in pull request #5272: [BYOC] Add example of Composite + Annotate for DNNL fused op
URL: https://github.com/apache/incubator-tvm/pull/5272#discussion_r406401569
 
 

 ##########
 File path: tests/python/relay/test_pass_partition_graph.py
 ##########
 @@ -856,6 +857,111 @@ def expected():
     partitioned = transform.PartitionGraph()(mod)
     assert tvm.ir.structural_equal(partitioned, ref_mod, map_free_vars=True)
 
+
+def test_partition_conv_bias_relu():
+    def make_pattern():
+        data = relay.var("data", relay.TensorType((1, 3, 224, 224), "float32"))
+        weight = relay.var("weight")
+        bias = relay.var("bias")
+        conv = relay.nn.conv2d(data=data, weight=weight, kernel_size=(3, 3),
+                               channels=8, padding=(1, 1))
+        add = relay.add(conv, bias)
+        return relay.nn.relu(add)
+
+    def get_blocks(prefix, data, in_channel, out_channel,
+                   include_bn=True, include_sigmoid=False):
+        weight = relay.var(prefix + "weight")
+        bn_gamma = relay.var(prefix + "bn_gamma")
+        bn_beta = relay.var(prefix + "bn_beta")
+        bn_mmean = relay.var(prefix + "bn_mean")
+        bn_mvar = relay.var(prefix + "bn_var")
+
+        layer = relay.nn.conv2d(data=data, weight=weight, kernel_size=(3, 3),
+                                channels=out_channel, padding=(1, 1))
+        if include_bn:
+            bn_output = relay.nn.batch_norm(layer, bn_gamma, bn_beta,
+                                            bn_mmean, bn_mvar)
+            layer = bn_output[0]
+        if include_sigmoid:
+            # dummy layer to prevent pattern detection
+            layer = relay.sigmoid(layer)
+        layer = relay.nn.relu(layer)
+        return layer
+
+    def get_net(include_bn=True, include_sigmoid=False):
+        data = relay.var("data", relay.TensorType((1, 3, 224, 224), "float32"))
+        layer1 = get_blocks("layer1_", data, 3, 8, include_bn, include_sigmoid)
+        layer2 = get_blocks("layer2_", layer1, 8, 8, include_bn, include_sigmoid)
+        return relay.Function(relay.analysis.free_vars(layer2), layer2)
+
+    def get_partitoned_mod(mod, params):
+        # This is required for constant folding
+        mod["main"] = bind_params_by_name(mod["main"], params)
+        pattern_table = [
+            ("dnnl.conv_bias_relu", make_pattern())
+        ]
+        remove_bn_pass = transform.Sequential([
+            transform.InferType(),
+            transform.SimplifyInference(),
+            transform.FoldConstant(),
+            transform.FoldScaleAxis(),
+        ])
+        composite_partition = transform.Sequential([
+            remove_bn_pass,
+            transform.MergeComposite(pattern_table),
+            transform.AnnotateTarget("dnnl"),
 
 Review comment:
   Hey I just tried your case with #5277 and it works fine. Maybe we can push to merge that PR so that this problem will be gone naturally.

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services