Mediapipe generic metrics demo #3054
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
dkalinowski
reviewed
Feb 11, 2025
| @@ -172,7 +173,7 @@ def display(self): | |||
| self.pq.put((sent_frame_id, received_frame, timestamp)) | |||
|
|
|||
| def get_timestamp(self) -> int: | |||
| return int(cv2.getTickCount() / cv2.getTickFrequency() * 1e6) | |||
| return int(time.time() * 1e6) | |||
There was a problem hiding this comment.
why this change? why do we still want to stamp it manually? should we rely on automatic stamping?
otherwise the metric is wrong - we take into account client->server network transfer time
There was a problem hiding this comment.
fixed that, now benchmarking is based on server side timestamps. Client side timestamps are now only used to order frames while using legacy(non-streaming) method.
dkalinowski
reviewed
Feb 11, 2025
| @@ -232,7 +233,7 @@ def start(self, *, ovms_address : str, input_name : str, model_name : str, datat | |||
| inputs=[grpcclient.InferInput(input_name, np_frame.shape, datatype.string())] | |||
| inputs[0].set_data_from_numpy(np_frame) | |||
| if streaming_api: | |||
| triton_client.async_stream_infer(model_name=model_name, inputs=inputs, parameters={"OVMS_MP_TIMESTAMP":self.get_timestamp()}) | |||
| triton_client.async_stream_infer(model_name=model_name, inputs=inputs) | |||
There was a problem hiding this comment.
why do we still have get_timestamp if we dont use it here?
bstrzele
force-pushed
the
mp_request_latency_metric
branch
from
bd053a3 to
5dd015b
Compare
bstrzele
force-pushed
the
mp_metrics_demo
branch
from
d6cef4d to
0e4a084
Compare
bstrzele
force-pushed
the
mp_request_latency_metric
branch
from
5dd015b to
43e1c69
Compare
bstrzele
force-pushed
the
mp_metrics_demo
branch
2 times, most recently
from
f97f626 to
87121dd
Compare
bstrzele
force-pushed
the
mp_request_latency_metric
branch
from
ef43bc6 to
df10202
Compare
bstrzele
force-pushed
the
mp_metrics_demo
branch
from
87121dd to
06489ea
Compare
dkalinowski
approved these changes
Feb 18, 2025
dtrawins
approved these changes
Feb 18, 2025
bstrzele
force-pushed
the
mp_request_latency_metric
branch
from
df10202 to
626fb8b
Compare
bstrzele
force-pushed
the
mp_metrics_demo
branch
from
06489ea to
6ef988d
Compare
bstrzele
force-pushed
the
mp_metrics_demo
branch
from
6ef988d to
e8a7d5f
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
🛠 Summary
JIRA/Issue if applicable.
Describe the changes.
🧪 Checklist
``