[GitHub] [tvm] junrushao1994 commented on a change in pull request #10079: [MetaSchedule][M4a] User-API: Tune-TE/TIR/Relay

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

junrushao1994 commented on a change in pull request #10079:
URL: https://github.com/apache/tvm/pull/10079#discussion_r793188970



##########
File path: python/tvm/meta_schedule/testing/relay_workload.py
##########
@@ -15,13 +15,230 @@
 # specific language governing permissions and limitations
 # under the License.
 """Workloads in Relay IR"""
+from enum import Enum
 from typing import Dict, Tuple
 
-import tvm.relay.testing  # pylint: disable=unused-import
 from tvm import relay
 from tvm.ir import IRModule
 from tvm.runtime import NDArray
 
+# Model types supported in Torchvision
+class MODEL_TYPE(Enum):  # pylint: disable=invalid-name

Review comment:
       I don't think we should define this huge chunk of models on mainline, at least not for now :-) Let's find alternatives 




-- 
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