Ankle/yolov5_birdproject
1
0 Fork 0
Code Issues Pull Requests Actions 6 Packages Projects Releases Wiki Activity
2,075 Commits 1 Branch 0 Tags
19f33cbae29ac2127dd877b52e228c178dda6086
Commit Graph
100 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Glenn Jocher 724d5b21b7 device_name="MYRIAD" for Intel NCS2 comment (#8327) 
Display device_name="MYRIAD" for Intel NCS2 option per user question in https://github.com/ultralytics/yolov5/issues/8154
 2022-06-24 14:18:58 +02:00
Glenn Jocher a2a1ed201d logging.ERROR on RANK not in (0, 1) (#8284) 
Improve DDP console response in https://github.com/ultralytics/yolov5/issues/8283
 2022-06-21 17:41:14 +02:00
Glenn Jocherandpre-commit-ci[bot] 1156a323f8 Created using Colaboratory (#8255) 
* Created using Colaboratory

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2022-06-18 14:29:32 +02:00
Glenn Jocher 669f707d62 process_batch() as numpy arrays (#8254) 
Avoid potential issues with deterministic ops. 

[ ] - verify for identical mAP to master
 2022-06-18 13:54:55 +02:00
Glenn Jocherandpre-commit-ci[bot] d6051382f1 HUB dataset_stats() error reporting (#8192) 
* HUB dataset_stats() error reporting

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Update dataloaders.py

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2022-06-17 18:37:08 +02:00
Glenn Jocher 303f3785ae Prefer MPS over CPU if available (#8210) 
* Prefer MPS over CPU if available

* Update torch_utils.py
 2022-06-17 18:28:29 +02:00
Glenn Jocher 86e6add07b Remove streaming source sleep period (#8243) 
Negatively impacts YouTube inference but removes any lag on webcams/RTSP/RTMP etc.

Resolves https://github.com/ultralytics/yolov5/issues/4465
 2022-06-17 17:59:27 +02:00
Glenn Jocherandpre-commit-ci[bot] 75bbaa8f44 Reject webcam inference on Colab/Kaggle (#8209) 
* Reject webcam inference on Colab/Kaggle

Improve user error understanding for https://github.com/ultralytics/yolov5/issues/8180

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* cleanup

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2022-06-14 14:28:21 +02:00
Glenn Jocherandpre-commit-ci[bot] c23a441c9d Improved dataset_stats() YAML checks (#8125) 
* Update dataloaders.py

* Update dataloaders.py

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2022-06-11 19:30:54 +02:00
Glenn Jocher 6adc53ba5f Docker GPU pip install opencv-python<4.6.0.66 (#8164) 
* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update
 2022-06-09 22:45:49 +02:00
Glenn Jocher 7c2691f9dc FROM nvcr.io/nvidia/pytorch:22.05-py3 (#8162) 2022-06-09 22:06:33 +02:00
Glenn Jocher 6e4661773e AutoBatch checks against failed solutions (#8159) 
* AutoBatch checks against failed solutions

@kalenmike this is a simple improvement to AutoBatch to verify that returned solutions have not already failed, i.e. return batch-size 8 when 8 already produced CUDA out of memory.

This is a halfway fix until I can implement a 'final solution' that will actively verify the solved-for batch size rather than passively assume it works.

* Update autobatch.py

* Update autobatch.py
 2022-06-09 17:15:49 +02:00
Glenn Jocher 18674e2f03 experimental.py Apple MPS device fix (#8121) 
* experimental.py Apple MPS fix

May resolve https://github.com/ultralytics/yolov5/issues/8102

* Update experimental.py

* Update experimental.py
 2022-06-06 23:58:50 +02:00
Glenn Jocher 47233e1698 Improved dataset error introspection (#8091) 
* Improved dataset error introspection

Intended to help https://github.com/ultralytics/yolov5/issues/8090

* Update general.py
 2022-06-03 12:45:51 +02:00
Glenn Jocher 7cef03dddd Fix torch long to float tensor on HUB macOS (#8067) 2022-06-01 17:34:46 +02:00
Glenn Jocher a80dd66efe Update stale.yml to 300 ops per run (#8061) 2022-05-31 20:18:40 +02:00
Glenn Jocher 7d87b9eae8 Make Docker actions conditional on ultralytics/yolov5 repo (#8060) 
* Update ci-testing.yml

* Update ci-testing.yml

* Update ci-testing.yml

* Update docker.yml
 2022-05-31 16:36:57 +02:00
Glenn Jocher 487edd5609 Dataset autodownload fstring updates 2022-05-31 12:36:20 +02:00
Glenn Jocher 258f4c6438 attempt_load() deserialize fix (#8051) 2022-05-31 10:55:14 +02:00
Glenn Jocher dcf8073881 Simplify and fix --save-period epoch 0 (#8042) 
Simplify and update `--save-period` epoch 0
 2022-05-30 12:42:12 +02:00
Glenn Jocher 632559b1e6 Add Dockerfile descriptions (#8031) 2022-05-29 20:43:01 +02:00
Glenn Jocher d490bdd7d6 Add best.pt PyTorch Hub inference to CI (#8024) 2022-05-28 22:55:03 +02:00
Glenn Jocher 7433d3829a Add requirements.txt protobuf<=3.20.1 (#8017) 
* Pin `protobuf==3.20.1`

* Update requirements.txt

* Update ci-testing.yml
 2022-05-28 12:12:27 +02:00
Glenn Jocher 5580b27daf check_requirements() "" Windows double quote (#8016) 2022-05-28 11:13:44 +02:00
Glenn Jocher 07e84370ac Pin CI protobuf==3.20.1 (#8015) 
Pin protobuf==3.20.1

Resolve protobuf 4 issues.
 2022-05-28 10:53:44 +02:00
Glenn Jocher bf1a6dda7b Update CI benchmarks to ONNX autoinstall (#8008) 
Avoids openvino-dev conflicts
 2022-05-27 16:54:18 +02:00
Glenn Jocher 09ba6f6eec Add warning emoji ⚠️ on --conf > 0.001 (#8005) 
* Add warning emoji on `--conf > 0.001`

* Update val.py
 2022-05-27 11:49:30 +02:00
Glenn Jocherandpre-commit-ci[bot] 2373c507b0 Update and add benchmarks to ci-testing.yml (#7996) 
* Update and rename ci-testing.yml to ci.yml

* Update ci.yml

* Update ci.yml

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Update and rename ci.yml to ci-tests.yml

* Update ci-tests.yml

* Update ci-tests.yml

* Rename ci-tests.yml to ci-testing.yml

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2022-05-27 11:46:55 +02:00
Glenn Jocher a6e99e4d66 cURL download double quotes (#7999) 
Attempt to resolve Windows issues
 2022-05-26 20:37:48 +02:00
Glenn Jocherandpre-commit-ci[bot] 980aace209 Add psutil and ipython to requirements.txt (#7998) 
* Add `psutil` and `ipython` to requirements.txt

Lightweight packages used by YOLOv5 for system utilization (psutil) and interactive notebooks (IPython)

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* sort alphabetically

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2022-05-26 19:12:19 +02:00
Glenn Jocher cd71aa3515 check_requirements() Windows fix (#7997) 2022-05-26 19:01:46 +02:00
Glenn Jocher 945579699a Remove formats variable to avoid pd conflict (#7993) 
* Remove `formats` variable to avoid `pd` conflict

* Update export.py
 2022-05-26 16:07:58 +02:00
Glenn Jocher 1dcb774998 Update requirements.txt with Usage example (#7966) 
Update requirements.txt
 2022-05-25 01:40:17 +02:00
Glenn Jocher 5d6fbb1e25 Update greetings.yml (#7965) 2022-05-24 23:32:21 +02:00
Glenn Jocher d07f9ce0ea AMP check improvements backup YOLOv5n pretrained (#7959) 
* Reduce AMP check to detections verification

More robust and faster

* Update general.py

* Update general.py
 2022-05-24 15:33:35 +02:00
Glenn Jocher 68ff6c9c08 Increase NMS fixed time limit 300ms + 30ms/img (#7957) 
* Increase NMS fixed time limit to 200ms

* Update general.py
 2022-05-24 14:11:03 +02:00
Glenn Jocher b5ebd47d64 Increase NMS time limit to 50 ms/img (#7956) 2022-05-24 13:58:10 +02:00
Glenn Jocher c215878f11 YOLOv5 Apple Metal Performance Shader (MPS) support (#7878) 
* Apple Metal Performance Shader (MPS) device support

Following https://pytorch.org/blog/introducing-accelerated-pytorch-training-on-mac/

Should work with Apple M1 devices with PyTorch nightly installed with command `--device mps`. Usage examples:
```bash
python train.py --device mps
python detect.py --device mps
python val.py --device mps
```

* Update device strategy to fix MPS issue
 2022-05-24 13:34:32 +02:00
Glenn Jocher 0dd66e2dc7 OpenVINO metadata fix (#7952) 
* Rename OpenVINO meta.yaml to model name

* Rename OpenVINO meta.yaml to model name

* Rename OpenVINO meta.yaml to model name

* fix
 2022-05-24 11:59:59 +02:00
Glenn Jocher 541a5b72bb Windows check_file() fix (#7938) 
Resolves Ultralytics HUB CI errors.
 2022-05-23 16:15:38 +02:00
Glenn Jocher 9b4e05439c Fix AMP check tolerance (#7937) 
Adjust to 5%, fixes failing Colab AMP check with V100 (1.5% different) with 200% safety margin.
 2022-05-23 15:57:16 +02:00
Glenn Jocher cf3fb58522 AMP check image download backup (#7936) 
Resolves https://github.com/ultralytics/yolov5/discussions/7931
 2022-05-23 15:31:54 +02:00
Glenn Jocherandpre-commit-ci[bot] cee5959c74 Code refactor (#7923) 
* Code refactor for general.py

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Update restapi.py

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2022-05-22 15:24:08 +02:00
Glenn Jocherandpre-commit-ci[bot] eb1217f3ac Add PyTorch AMP check (#7917) 
* Add PyTorch AMP check

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Cleanup

* Cleanup

* Cleanup

* Robust for DDP

* Fixes

* Add amp enabled boolean to check_train_batch_size

* Simplify

* space to prefix

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2022-05-22 13:41:18 +02:00
Glenn Jocher 547c89b3a0 Add --keras argument for TF exports (#7921) 
Resolves https://github.com/ultralytics/yolov5/issues/7911#issuecomment-1133671255
 2022-05-22 13:33:36 +02:00
Glenn Jocher 15057d2a34 Add check_yaml() to benchmarks.py (#7916) 
Locate file in subdirectories.
 2022-05-21 19:39:19 +02:00
Glenn Jocherandpre-commit-ci[bot] 5774a1514d Add DWConvTranspose2d() module (#7881) 
* Add DWConvTranspose2d() module

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Add DWConvTranspose2d() module

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Fix

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Fix

* Fix

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2022-05-20 16:13:40 +02:00
Glenn Jocher a9a92aec5c cv2.resize interpolation fix (#7903) 
Fix for https://github.com/ultralytics/yolov5/discussions/7901
 2022-05-20 12:59:05 +02:00
Glenn Jocher 7d46c69235 Invert Docker Image publishing order (#7877) 
To appear on Docker Hub in top down order:

- latest
- latest-cpu
- latest-arm64
 2022-05-18 17:23:42 +02:00
Glenn Jocher 9a7f289eed Update Dockerfile-arm64 (#7860) 
* Update Dockerfile-arm64

* Update docker.yml
 2022-05-17 16:35:12 +02:00
Glenn Jocher 1b8e70f037 Add TFDWConv() depth_multiplier (#7858) 
Enabled grouped non c1 == c2 convolutions in TF YOLOv5 models.
 2022-05-17 15:42:36 +02:00
Glenn Jocher 91c82d8f92 Update Dockerfile-cpu install libpython3.8-dev (#7857) 
* Update Dockerfile-cpu install `libpython3.8-dev`

Fix OpenVINO export

* Update Dockerfile-arm64
 2022-05-17 15:09:10 +02:00
Glenn Jocherandpre-commit-ci[bot] d7d2b10f69 Create docker.yml (#7856) 
* Create docker.yml

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Update docker.yml

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Update docker.yml

* Update docker.yml

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Cleanup

* Cleanup2

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2022-05-17 14:11:38 +02:00
Glenn Jocher e4d82c1951 Update CI CPU badge (#7855) 
* Update README.md

* Update greetings.yml
 2022-05-17 13:01:18 +02:00
Glenn Jocher 614ef110b3 Update Dockerfile --no-install-recommends (#7846) 
* Update Dockerfile-cpu `--no-install-recommends`

Per https://ubuntu.com/blog/we-reduced-our-docker-images-by-60-with-no-install-recommends

* Update Dockerfile-M1

* Update Dockerfile

* Update Dockerfile-M1

* Update Dockerfile-cpu
 2022-05-17 01:29:23 +02:00
Glenn Jocher b52fd48b4a TFDWConv() depthwise_initializer fix (#7845) 2022-05-16 23:37:38 +02:00
Glenn Jocher 2b64b45cd8 Fix TFDWConv() c1 == c2 check (#7842) 2022-05-16 18:06:46 +02:00
Glenn Jocherandpre-commit-ci[bot] fb7fa5be8b New TensorFlow TFCrossConv() module (#7827) 
* New TensorFlow `TFCrossConv()` module

* Move from experimental to common

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Add C3x

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Add to C3x to yolo.py

* Add to C3x to tf.py

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* TFC3x bug fix

* TFC3x bug fix

* TFC3x bug fix

* Add TFDWConv g==c1==c2 check

* Add comment

* Update tf.py

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2022-05-16 17:02:16 +02:00
Glenn Jocher 4d59f65db5 New TensorFlow TFDWConv() module (#7824) 
* New TensorFlow `TFDWConv()` module

Analog to DWConv() module:
https://github.com/ultralytics/yolov5/blob/8aa2085a7e7ae20a17a7548edefbdb2960f2b29b/models/common.py#L53-L57

* Fix and new activations() function

* Update tf.py
 2022-05-16 01:04:16 +02:00
Glenn Jocher 1e112ced79 YOLOv5 OpenVINO PyTorch Hub inference fix (#7826) 
Resolves bug report #7817
 2022-05-16 00:56:44 +02:00
Glenn Jocher 8aa2085a7e Refactor modules (#7823) 2022-05-15 19:44:16 +02:00
Glenn Jocher f00071416f Refactor collections and fstrings (#7821) 
* Update torch_utils.py

* Additional code refactoring

* tuples to sets

* Cleanup
 2022-05-15 16:38:26 +02:00
Glenn Jocher 3356f2609c Add Python version output (#7814) 2022-05-14 18:30:47 +02:00
Glenn Jocherandpre-commit-ci[bot] 4a295b1a89 Add @threaded decorator (#7813) 
* Add `@threaded` decorator

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2022-05-14 16:12:08 +02:00
Glenn Jocher 9d8ed37df7 Rename utils/datasets.py > utils/dataloaders.py (#7799) 2022-05-13 14:34:16 +02:00
Glenn Jocher 5e077bfd39 Add Dockerfile-M1 (#7720) 
* Add Dockerfile-M1

* Update

* Update

* Update Dockerfile-M1
 2022-05-13 14:15:21 +02:00
Glenn Jocher 8a4175cde0 Add smoothing to curve plots and max F1 index (#7798) 
@sergiossm
 2022-05-13 13:53:21 +02:00
Glenn Jocherandpre-commit-ci[bot] d95a728f55 Implement DDP static_graph=True (#6940) 
* Implement DDP `static_graph=True`

Experimental implementation of new PyTorch 1.11.0 DDP feature.

* Add 1.11.0 check

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2022-05-13 12:32:47 +02:00
Glenn Jocherandpre-commit-ci[bot] f3fecf94a9 Pin downloads to release version (#7790) 
* Pin downloads to release version

Fixes a release version to avoid forward-compatibility issues in future releases.

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2022-05-13 00:24:53 +02:00
Glenn Jocher d059d1da03 Report fused model summary by default (#7722) 2022-05-06 23:51:59 -07:00
Glenn Jocher aa7a0e91b1 Update on_train_end callback (#7716) 2022-05-05 21:25:13 -07:00
Glenn Jocherandpre-commit-ci[bot] 1d0a0944c1 Update tutorial.ipynb (#7715) 
* Update tutorial.ipynb

* Created using Colaboratory

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2022-05-05 20:55:52 -07:00
Glenn Jocher c4cb7c684a Update README.md (#7686) 2022-05-03 15:18:01 -07:00
Glenn Jocherandpre-commit-ci[bot] d4ea61e043 FROM nvcr.io/nvidia/pytorch:22.04-py3 (#7680) 
* FROM nvcr.io/nvidia/pytorch:22.04-py3

* Update Docker

* Update Docker

* Update Docker

* Update Docker

* Update TRT auto-install

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Cleanup

* Cleanup

* Cleanup cpu

* Cleanup cpu

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2022-05-03 13:47:30 -07:00
Glenn Jocher e305aba686 Pin Docker-cpu FROM ubuntu:20.04 (#7677) 2022-05-02 23:27:24 -07:00
Glenn Jocher c4862fcd31 Update Dockerfile-cpu to force python3.9 (#7675) 
* Update

* Update

* Do not install torch

* Pillow>9.1

* Update Dockerfile-cpu

* Update Dockerfile-cpu

* Update Dockerfile-cpu

* Update Dockerfile-cpu

* Update Dockerfile-cpu

* Update Dockerfile-cpu

* Update Dockerfile-cpu

* Update Dockerfile-cpu

* Update Dockerfile-cpu

* Update Dockerfile

* fix emoji

* reduce scipy

* add libpython3.9

* Update Dockerfile
 2022-05-02 20:53:02 -07:00
Glenn Jocher 488fb0a36a Bump scipy>=1.5 to meet numpy constraints (#7646) 
Resolves https://github.com/ultralytics/yolov5/issues/7638
 2022-04-29 12:00:30 -07:00
Glenn Jocher b24a576823 Reduce opencv-python>=4.1.1 for Jetson Nano (#7645) 
May help https://github.com/ultralytics/yolov5/issues/7631#issuecomment-1113007451
 2022-04-29 11:50:30 -07:00
Glenn Jocher 1a3ecb8b38 increment_path() robustness improvements (#7628) 
Improved robustness to filename edge cases like `data/images/zidane.23.jpg` that currently fail. May resolve https://github.com/ultralytics/yolov5/issues/7432
 2022-04-28 14:00:43 -07:00
Glenn Jocher b53917de8d Remove tqdm.auto (#7599) 2022-04-26 15:00:01 -07:00
Glenn Jocher e54e758cfb Add PyTorch-only benchmark arg (#7564) 
Usage:
```
python utils/benchmarks.py --weights yolov5s.pt --img 640 --pt-only
```
 2022-04-24 20:03:23 -07:00
Glenn Jocher 950a85d9f6 TensorRT PyTorch Hub inference fix (#7560) 
Solution proposed in https://github.com/ultralytics/yolov5/issues/7128 to TRT PyTorch Hub CUDA illegal memory errors.
 2022-04-24 12:45:56 -07:00
Glenn Jocher c16671fc74 Add print(results) override for PyTorch Hub results (#7559) 2022-04-24 12:07:05 -07:00
Glenn Jocher be67572279 Enable results.print() when _verbose=False (#7558) 
Follows implementation of _verbose flag for PyTorch Hub models. Currently these are so silent that result.print() does nothing 😂
 2022-04-24 11:30:40 -07:00
Glenn Jocherandpre-commit-ci[bot] 7043872f25 PyTorch Hub _verbose=False fix2 (#7550) 
* PyTorch Hub `_verbose=False` fix2

* Update downloads.py

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Update hubconf.py

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Update

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Update

* Update

* Update

* Update

* Update

* Update

* Update

* Update

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2022-04-23 11:26:25 -07:00
Glenn Jocher 1f1ec1c3e7 Restrict TRT autoinstall to Linux-only (#7549) 
May partially resolve concerns in https://github.com/ultralytics/yolov5/pull/7537#discussion_r856843711
 2022-04-23 09:36:36 -07:00
Glenn Jocherandpre-commit-ci[bot] 404b4fefbe Update restapi.py (#7309) 
* Update restapi.py

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Update restapi.py

* Update restapi.py

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Update restapi.py

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2022-04-22 16:19:21 -07:00
Glenn Jocherandpre-commit-ci[bot] 3a89377c04 Improve availability of YOLOv5 in Russia (#7545) 
* Add redundant weights download mirrors

This PR seeks to improve access worldwide to YOLOv5 weights. Universal access to AI for all is our core value, and we are against any censorship or restriction efforts.

I've uploaded the official YOLOv5 v6.1 weights to a primary backup bucket on GCP and to secondary backup on Google Drive at https://drive.google.com/drive/folders/1EFQTEUeXWSFww0luse2jB9M1QNZQGwNl. Autodownload with try the first two locations (GitHuB release assets and GCP bucket), and point users to the Google Drive folder if the first two fail.

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2022-04-22 16:07:33 -07:00
Glenn Jocher f62609eb52 Update check_requirements() with cmds=() argument (#7543) 2022-04-22 14:31:05 -07:00
Glenn Jocher e04d8b1cb0 Update precommit monthly python 3.7+ (#7542) 2022-04-22 13:43:50 -07:00
Glenn Jocherandpre-commit-ci[bot] cc1d7df03c Autoinstall TensorRT if missing (#7537) 
* Autoinstall TensorRT if missing

May resolve https://github.com/ultralytics/yolov5/issues/7464

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Update export.py

* Update export.py

* Update export.py

* Update export.py

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2022-04-22 12:31:33 -07:00
Glenn Jocher 813eba85b2 Empty val batch CUDA device fix (#7539) 
Verified fix for https://github.com/ultralytics/yolov5/pull/7525#issuecomment-1106081123
 2022-04-22 12:01:14 -07:00
Glenn Jocher b804b36bc4 Add Docker --file argument to build (#7527) 2022-04-21 20:31:26 -07:00
Glenn Jocher d2e698c75c Reduce val device transfers (#7525) 2022-04-21 20:06:57 -07:00
Glenn Jocher 23718df1c6 Fix val plots=plots (#7524) 2022-04-21 18:21:01 -07:00
Glenn Jocher 918d7b2b3f Refactor Dockerfiles to utils/docker (#7510) 
* Refactor Docker files

* Refactor Docker files

* Update Dockerfile
 2022-04-20 14:23:55 -07:00
Glenn Jocher 3f3852e2ff Fix val.py Ensemble() (#7490) 2022-04-19 21:15:04 -07:00
Glenn Jocher ab5b917494 check_fonts() download to CONFIG_DIR fix (#7489) 
Follows https://github.com/ultralytics/yolov5/pull/7488. Correct bug where fonts were downloading to current working directory rather than global CONFIG_DIR
 2022-04-19 17:50:02 -07:00
Glenn Jocherandpre-commit-ci[bot] c9042dc2ad Improved non-latin Annotator() plotting (#7488) 
* Improved non-latin labels Annotator plotting

May resolve https://github.com/ultralytics/yolov5/issues/7460

* Update train.py

* Update train.py

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* add progress arg

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
 2022-04-19 17:32:15 -07:00
Glenn Jocher c9a3b14a74 Disable pbar for DDP ranks > 0 (#7440) 2022-04-16 15:12:38 +02:00