-
Notifications
You must be signed in to change notification settings - Fork 0
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
update detect.py
for torchscript support
#1
Commits on Oct 9, 2021
-
update
detect.py
for torchscript supportSimple update for torchscript support. Assumes the torchscript file has been generated with `export.py`
Configuration menu - View commit details
-
Copy full SHA for e2379fa - Browse repository at this point
Copy the full SHA e2379faView commit details -
Add
requests
to requirements.txt (ultralytics#5112)* Requirements updated 1. Requests added to requirements.txt. That might not be included in all docker base images, adding it to the requirements is safer. 2. Added a minimum version to Pandas. It's a good practice to have versions for all dependencies. * Sort alphabetically * Update requirements.txt Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Configuration menu - View commit details
-
Copy full SHA for 97b6b14 - Browse repository at this point
Copy the full SHA 97b6b14View commit details
Commits on Oct 10, 2021
-
Pass
LOCAL_RANK
totorch_distributed_zero_first()
(ultralytics#5114)Co-authored-by: qiningonline <qiningonline@gmail.com>
Configuration menu - View commit details
-
Copy full SHA for 4a6dfff - Browse repository at this point
Copy the full SHA 4a6dfffView commit details -
Fix different devices bug when moving model from GPU to CPU (ultralyt…
…ics#5110) * fix different devices bug * extend _apply() instead of to() for a general fix * Only apply if Detect() is last layer Co-authored-by: Jebastin Nadar <njebastin10@gmail.com> * Indent fix * Add comment to yolo.py * Add comment to common.py Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Configuration menu - View commit details
-
Copy full SHA for a0e1504 - Browse repository at this point
Copy the full SHA a0e1504View commit details -
Configuration menu - View commit details
-
Copy full SHA for 4f9718a - Browse repository at this point
Copy the full SHA 4f9718aView commit details
Commits on Oct 11, 2021
-
Configuration menu - View commit details
-
Copy full SHA for ba4b79d - Browse repository at this point
Copy the full SHA ba4b79dView commit details -
Update val.py
pad = 0.0 if task == speed else 0.5
(ultralytics#5121)* Update val.py `pad = 0.0 if task == speed else 0.5` * Cleanup
Configuration menu - View commit details
-
Copy full SHA for 7d37b3c - Browse repository at this point
Copy the full SHA 7d37b3cView commit details -
Configuration menu - View commit details
-
Copy full SHA for 4cf7d48 - Browse repository at this point
Copy the full SHA 4cf7d48View commit details -
Fix
ROOT
as relative path (ultralytics#5129)* use os.path.relpath instead of relative_to * use os.path.relpath instead of relative_to * Remove os.path from val.py * Remove os.path from train.py * Update detect.py import to os * Update export.py import to os Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Configuration menu - View commit details
-
Copy full SHA for 153873e - Browse repository at this point
Copy the full SHA 153873eView commit details -
Refactor
Detect()
anchors for ONNX <> OpenCV DNN compatibility (ult……ralytics#4833) * refactor anchors and anchor_grid in Detect Layer * fix CI failures by adding compatibility * fix tf failure * fix different devices errors * Cleanup * fix anchors overwriting issue * better refactoring * Remove self.anchor_grid shape check (redundant with self.grid check) Also PEP8 / 120 line width * Convert _make_grid() from static to dynamic method * Remove anchor_grid.to(device) clone() should already clone to same device as self.anchors * fix different devices error Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Configuration menu - View commit details
-
Copy full SHA for 9d75e42 - Browse repository at this point
Copy the full SHA 9d75e42View commit details -
Add OpenCV DNN option for ONNX inference (ultralytics#5136)
* Add OpenCV DNN option for ONNX inference Usage: ```bash python detect.py --weights yolov5s.onnx # ONNX Runtime inference python detect.py --weights yolov5s.onnx -dnn # OpenCV DNN inference ``` * DNN prediction to tensor * Update detect.py
Configuration menu - View commit details
-
Copy full SHA for 0bf24cf - Browse repository at this point
Copy the full SHA 0bf24cfView commit details
Commits on Oct 12, 2021
-
Configuration menu - View commit details
-
Copy full SHA for 14a3b8f - Browse repository at this point
Copy the full SHA 14a3b8fView commit details