A PyTorch implementation of the YOLOX object detection model based on the mmdetection implementation.
Project description
cjm-yolox-pytorch
Install
pip install cjm_yolox_pytorch
How to use
from cjm_yolox_pytorch.model import MODEL_TYPES, build_model
Select model type
model_type = MODEL_TYPES[0]
model_type
'yolox_tiny'
Build YOLOX model
import torch
yolox = build_model(model_type, 19)
test_inp = torch.randn(1, 3, 256, 256)
with torch.no_grad():
cls_scores, bbox_preds, objectness = yolox(test_inp)
print(f"cls_scores: {[cls_score.shape for cls_score in cls_scores]}")
print(f"bbox_preds: {[bbox_pred.shape for bbox_pred in bbox_preds]}")
print(f"objectness: {[objectness.shape for objectness in objectness]}")
cls_scores: [torch.Size([1, 19, 32, 32]), torch.Size([1, 19, 16, 16]), torch.Size([1, 19, 8, 8])]
bbox_preds: [torch.Size([1, 4, 32, 32]), torch.Size([1, 4, 16, 16]), torch.Size([1, 4, 8, 8])]
objectness: [torch.Size([1, 1, 32, 32]), torch.Size([1, 1, 16, 16]), torch.Size([1, 1, 8, 8])]
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
cjm-yolox-pytorch-0.0.107.tar.gz
(22.7 kB
view hashes)
Built Distribution
Close
Hashes for cjm-yolox-pytorch-0.0.107.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | c1d6460c5669cd71b2c4226346f0558e44e7d7381cae3d8d8763a3e024f83b7a |
|
MD5 | 449809a81848839c4d2573a0f2987c27 |
|
BLAKE2b-256 | dac8764bf0ad77ceddce342046597ee9402029551c428e203d2161362ce10430 |
Close
Hashes for cjm_yolox_pytorch-0.0.107-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | d9264c292ff707d66d234c3944aa9e923a3ceb9406ba4b7b2582649ce3c1300f |
|
MD5 | 2d220372a598f8da1930c10994905fac |
|
BLAKE2b-256 | 3cc08c4d160281a3ed1bfdf314318d1df9620dd6cb90db21595c7b3d9aff1b0d |