No project description provided
Project description
Yolov5 support for Rikai
rikai-yolov5
integrates Yolov5 implemented in PyTorch with Rikai. It is based
on the packaged ultralytics/yolov5.
Notebooks
Usage
There are two ways to use rikai-yolov5
.
rikai.mlflow.pytorch.log_model(
model,
"model",
OUTPUT_SCHEMA,
registered_model_name=registered_model_name,
model_type="yolov5",
)
Another way is setting the model_type in Rikai SQL:
CREATE MODEL mlflow_yolov5_m
MODEL_TYPE yolov5
OPTIONS (
device='cpu'
)
USING 'mlflow:///{registered_model_name}';
Available Options
Name | Default Value | Description |
---|---|---|
conf_thres | 0.25 | NMS confidence threshold |
iou_thres | 0.45 | NMS IoU threshold |
max_det | 1000 | maximum number of detections per image |
image_size | 640 | Image width |
Here is a sample usage of the above options:
CREATE MODEL mlflow_yolov5_m
OPTIONS (
device='cpu',
iou_thres=0.5
)
USING 'mlflow:///{registered_model_name}';
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
rikai-yolov5-0.1.0.tar.gz
(8.4 kB
view hashes)
Built Distribution
Close
Hashes for rikai_yolov5-0.1.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 8935da31b205ed18d56b14418a6a7102ad9fb3416e73dc56335c9767475d764e |
|
MD5 | 766f0cbcfc724378751f95711867dec5 |
|
BLAKE2b-256 | 3810712ad514de9d6444d7e7317a4c7ae18d875a3b95f97e9795a5ad0812e2de |