[GitHub] [tvm] lhutton1 commented on a change in pull request #9508: [microNPU] Update Conv2D Tests to Use TF API to Gen Test Cases

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

lhutton1 commented on a change in pull request #9508:
URL: https://github.com/apache/tvm/pull/9508#discussion_r756916762



##########
File path: tests/python/contrib/test_ethosu/test_codegen.py
##########
@@ -48,123 +47,184 @@ def get_shape_expr(in_expr, out_expr):
     return shape
 
 
-@pytest.mark.parametrize(
-    "accel_type",
-    ACCEL_TYPES,
-)
-def test_ethosu_conv2d(accel_type):
-    def create_graph_single(input_tensor_name, input_tensor_shape, input_tensor_dtype):
-        c1_params = relay_ir_builder.QnnConv2DParams(input_tensor_dtype)
-        c1_params.ifm.shape = input_tensor_shape
-        c1_params.kernel.shape = (3, 3, c1_params.ifm.shape[3], 32)
-        c1_params.kernel.sc = relay.const(np.random.rand(32) * 2, "float32")
-        c1_params.strides = (1, 1)
-        c1_params.pad = "VALID"
-        c1_params.update_output_qnn_params(
-            input_tensor_dtype, input_tensor_dtype, input_tensor_dtype
-        )
-        input0 = relay.var(input_tensor_name, shape=c1_params.ifm.shape, dtype=c1_params.ifm.dtype)
-        c1, new_params = relay_ir_builder.create_qnn_conv2d(c1_params, input0)
-        c1_params.ofm.shape = get_shape_expr(input0, c1)
+@pytest.mark.parametrize("ifm_shape", [(1, 299, 299, 3), (1, 55, 55, 3)])
+@pytest.mark.parametrize("kernel_shape", [(3, 2), (1, 3)])
+@pytest.mark.parametrize("strides, dilation", [((1, 1), (2, 1)), ((3, 2), (1, 1))])
+@pytest.mark.parametrize("padding", ["SAME", "VALID"])
+@pytest.mark.parametrize("accel_type", ACCEL_TYPES)
+@pytest.mark.parametrize("activation", None, "relu")

Review comment:
       Nit: Lets use `"RELU"` to be consistent with other tests

##########
File path: tests/python/contrib/test_ethosu/test_legalize.py
##########
@@ -221,135 +221,135 @@ def get_shape_expr(in_expr, out_expr):
     return shape
 
 
+def compute_ofm_shape(ifm_shape, padding, kernel_shape, strides, dilation):
+    if padding.lower() == "valid":
+        h = math.ceil((ifm_shape[1] - (kernel_shape[0] - 1) * dilation[0]) / strides[0])
+        w = math.ceil((ifm_shape[2] - (kernel_shape[1] - 1) * dilation[1]) / strides[1])
+    if padding.lower() == "same":
+        h = math.ceil(ifm_shape[1] / strides[0])
+        w = math.ceil(ifm_shape[2] / strides[1])
+    ofm_shape = [ifm_shape[0], h, w, kernel_shape[3]]
+    return ofm_shape

Review comment:
       Just wondering if there was a reason the function in `infra.py` didn't work?




-- 
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.

To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org