-
-
Notifications
You must be signed in to change notification settings - Fork 3.4k
GCP Quickstart
Glenn Jocher edited this page Mar 25, 2019
·
24 revisions
-
Select a premade pytorch image from the GCP marketplace, check 'install GPU driver automatically': https://cloud.google.com/deep-learning-vm/docs/images
-
Install the dependencies:
conda install numpy opencv tqdm && conda install pytorch torchvision -c pytorch
- Paste the following code. No other steps are required.
sudo rm -rf yolov3 && git clone https://github.com/ultralytics/yolov3
bash yolov3/data/get_coco_dataset.sh
sudo rm -rf cocoapi && git clone https://github.com/cocodataset/cocoapi && cd cocoapi/PythonAPI && make && cd ../.. && cp -r cocoapi/PythonAPI/pycocotools yolov3
cd yolov3 && python3 test.py --save-json --conf-thres 0.001 --img-size 416
![Screenshot 2019-03-25 at 15 58 47](https://user-images.githubusercontent.com/26833433/54930106-f8968680-4f16-11e9-9c6d-a146df6875e7.png)
© 2024 Ultralytics Inc. All rights reserved.
https://ultralytics.com