lucifer443 / Spinenet Pytorch
Licence: apache-2.0
This project is a kind of implementation of SpineNet(CVPR 2020) using mmdetection.
Stars: ✭ 75
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Spinenet Pytorch
mmrazor
OpenMMLab Model Compression Toolbox and Benchmark.
Stars: ✭ 644 (+758.67%)
Mutual labels: detection, nas
Parser Javascript
Browser sniffing gone too far — A useragent parser library for JavaScript
Stars: ✭ 66 (-12%)
Mutual labels: detection
Eyevis
Android based Vocal Vision for Visually Impaired. Object Detection, Voice Assistance, Optical Character Reader, Read Aloud, Face Recognition, Landmark Recognition, Image Labelling etc.
Stars: ✭ 48 (-36%)
Mutual labels: detection
Math object detection
An image recognition/object detection model that detects handwritten digits and simple math operators. The output of the predicted objects (numbers & math operators) is then evaluated and solved.
Stars: ✭ 52 (-30.67%)
Mutual labels: detection
Unet Segmentation
The U-Net Segmentation plugin for Fiji (ImageJ)
Stars: ✭ 62 (-17.33%)
Mutual labels: detection
Social Media Depression Detector
😔 😞 😣 😖 😩 Detect depression on social media using the ssToT method introduced in our ASONAM 2017 paper titled "Semi-Supervised Approach to Monitoring Clinical Depressive Symptoms in Social Media"
Stars: ✭ 45 (-40%)
Mutual labels: detection
Autodl Projects
Automated deep learning algorithms implemented in PyTorch.
Stars: ✭ 1,187 (+1482.67%)
Mutual labels: nas
Shape Adaptor
The implementation of "Shape Adaptor: A Learnable Resizing Module" [ECCV 2020].
Stars: ✭ 59 (-21.33%)
Mutual labels: nas
Breachdetector
Detect root, emulation, debug mode and other security concerns in your Xamarin apps
Stars: ✭ 57 (-24%)
Mutual labels: detection
Once For All
[ICLR 2020] Once for All: Train One Network and Specialize it for Efficient Deployment
Stars: ✭ 1,127 (+1402.67%)
Mutual labels: nas
Jacinto Ai Devkit
Training & Quantization of embedded friendly Deep Learning / Machine Learning / Computer Vision models
Stars: ✭ 49 (-34.67%)
Mutual labels: detection
Flask weather
☀️ ☔️ Flask app to auto-detect local weather based off of user's IP address.
Stars: ✭ 70 (-6.67%)
Mutual labels: detection
Vww
[LPIRC 2019] First place in the Visual Wake Words challenge (TF-lite track)
Stars: ✭ 56 (-25.33%)
Mutual labels: nas
Efficientdet
EfficientDet (Scalable and Efficient Object Detection) implementation in Keras and Tensorflow
Stars: ✭ 1,116 (+1388%)
Mutual labels: detection
Kaggle Rsna
Deep Learning for Automatic Pneumonia Detection, RSNA challenge
Stars: ✭ 74 (-1.33%)
Mutual labels: detection
Ftcvision
Computer Vision library for FIRST Tech Challenge
Stars: ✭ 73 (-2.67%)
Mutual labels: detection
SpineNet-Pytorch
SpineNet is a CVPR 2020 paper for object detection. This project is a kind of implementation of SpineNet using mmdetection.
It is based on the
- the paper SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization
- official TensorFlow implementation
Models
Variant | mAP | Params | FLOPs | mAP in paper | Params in paper | FLOPs in paper |
---|---|---|---|---|---|---|
SpineNet-49S | 39.1 | 11.15M | 30.04B | 39.9 | 12.0M | 33.8B |
SpineNet-49 | 42.7 | 28.31M | 83.7B | 42.8 | 28.5M | 85.4B |
SpineNet-96 | —— | 42.74M | 261.35B | 47.1 | 43.0M | 265.4B |
SpineNet-143 | —— | —— | —— | 48.1 | 66.9M | 524.4B |
SpineNet-190 | —— | —— | —— | —— | 163.6M | 1885B |
Note: The parameters and flops are a little different from paper, so I think there are some difference between my code and official's code. More information about models can see in MODEL_DETAILS.md
Usage
-
Install mmdetection
This implementation is based on mmdetection(v1.1.0+8732ed9). Please refer to INSTALL.md for installation and dataset preparation.
-
Copy the codes to mmdetection directory
cp -r mmdet/ ${MMDETECTION_PATH}/ cp -r configs/ ${MMDETECTION_PATH}/
-
Prepare data
The directories should be arranged like this:
> mmdetection > ├── mmdet > ├── tools > ├── configs > ├── data > │ ├── coco > │ │ ├── annotations > │ │ ├── train2017 > │ │ ├── val2017 > │ │ ├── test2017
-
Train D0 with 4 GPUs
CONFIG_FILE=configs/spinenet/spinenet_49_B_8gpu.py ./ tools/dist_train.py ${CONFIG_FILE} 4
-
Calculate parameters and flops
python tools/get_flops.py ${CONFIG_FILE} --shape $SIZE $SIZE
-
Test
python tools/test.py ${CONFIG_FILE} ${CHECKPOINT_FILE} --out ${OUTPUT_FILE} --eval bbox
More usages can reference mmdetection documentation.
Update log
- [2020-05-30] Add SpineNet-49S results.
- [2020-05-13] Update codes and results.
- [2020-05-02] Create this repository.
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].