[GitHub] [tvm] masahi commented on a diff in pull request #13271: [Hexagon] Lint tests part 2

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

masahi commented on code in PR #13271:
URL: https://github.com/apache/tvm/pull/13271#discussion_r1014450161


##########
tests/python/contrib/test_hexagon/metaschedule_e2e/test_resnet50_fp16.py:
##########
@@ -44,14 +40,19 @@ def convert_conv2d_layout(mod, desired_layouts):
 @pytest.mark.skip("End-to-end tuning is skipped on CI.")
 @tvm.testing.requires_hexagon
 def test_resnet50(hexagon_launcher):
+    """Test Resnet50."""
+    model_json = "resnet50_fp16.json"
+    target_llvm = tvm.target.Target("llvm")
+    target_hexagon = get_hexagon_target("v69")
+
     if not os.path.exists(model_json):
         pytest.skip(msg="Run python export_models.py first.")
 
-    with open(model_json, "r") as fi:
-        mod = tvm.ir.load_json(fi.read())
+    with open(model_json, "r") as file:
+        mod = tvm.ir.load_json(file.read())
 
-    with open(model_params, "rb") as fi:
-        params = relay.load_param_dict(fi.read())
+    with open("resnet50_fp16.params", "rb") as file:

Review Comment:
   Can you restore the `model_params` variable rather than hard-coding it? The same comment for `test_resnet50_int8.py`.



-- 
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