Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
Thefalley
/
yolov4-leaky-416-int8-qop
like
1
Object Detection
ONNX
English
onnxruntime
yolov4
int8
coco
fpga
arxiv:
2004.10934
License:
mit
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
yolov4-leaky-416-int8-qop
653 MB
Ctrl+K
Ctrl+K
1 contributor
History:
38 commits
Thefalley
Add Visual comparison (FP32 vs INT8) section to model card
20e53b1
verified
about 1 month ago
images
Add inference example: compare_traffic.png
about 1 month ago
inference_outputs
Add inference output: inference_bus.png (generated by the published INT8 ONNX)
about 1 month ago
.gitattributes
2.75 kB
Add inference output: inference_bus.png (generated by the published INT8 ONNX)
about 1 month ago
LICENSE
1.46 kB
Add MIT LICENSE
about 1 month ago
NOTICE.md
4.52 kB
Add NOTICE.md (clean MIT chain)
about 1 month ago
README.md
5.15 kB
Add Visual comparison (FP32 vs INT8) section to model card
about 1 month ago
inference.py
8.92 kB
Add inference script with decoder
about 1 month ago
quantize_float_to_int8.py
3.19 kB
Add reproducible quantization script
about 1 month ago
yolov4-leaky-416_float.onnx
257 MB
xet
Add float ONNX (raw outputs)
about 1 month ago
yolov4-leaky-416_int8_qop.onnx
64.7 MB
xet
Add INT8 QOperator ONNX
about 1 month ago
yolov4_float.onnx
Safe
257 MB
xet
Add float ONNX (intermediate, pre-quantization)
about 2 months ago
yolov4_int8_qop.onnx
Safe
64.6 MB
xet
Add INT8 ONNX (QOperator)
about 2 months ago