PyTorch-Encoding
GluonCV-Torch
Load GluonCV Models in PyTorch.
Simply import gluoncvth to getting better pretrained model than torchvision:
import gluoncvth as gcv
model = gcv.models.resnet50(pretrained=True)
Installation:
pip install gluoncv-torch
Available Models
ImageNet
ImageNet models single-crop error rates, comparing to the torchvision models:
| torchvision | gluoncvth | |||
|---|---|---|---|---|
| Model | Top-1 error | Top-5 error | Top-1 error | Top-5 error |
| ResNet18 | 30.24 | 10.92 | 29.06 | 10.17 |
| ResNet34 | 26.70 | 8.58 | 25.35 | 7.92 |
| ResNet50 | 23.85 | 7.13 | 22.33 | 6.18 |
| ResNet101 | 22.63 | 6.44 | 20.80 | 5.39 |
| ResNet152 | 21.69 | 5.94 | 20.56 | 5.39 |
| Inception v3 | 22.55 | 6.44 | 21.33 | 5.61 |
More models available at GluonCV Image Classification ModelZoo
Semantic Segmentation
Results on Pascal VOC dataset:
| Model | Base Network | mIoU |
|---|---|---|
| FCN | ResNet101 | 83.6 |
| PSPNet | ResNet101 | 85.1 |
| DeepLabV3 | ResNet101 | 86.2 |
Results on ADE20K dataset:
| Model | Base Network | PixAcc | mIoU |
|---|---|---|---|
| FCN | ResNet101 | 80.6 | 41.6 |
| PSPNet | ResNet101 | 80.8 | 42.9 |
| DeepLabV3 | ResNet101 | 81.1 | 44.1 |
Quick Demo
import torch
import gluoncvth
# Get the model
model = gluoncvth.models.get_deeplab_resnet101_ade(pretrained=True)
model.eval()
# Prepare the image
url = 'https://github.com/zhanghang1989/image-data/blob/master/encoding/' + \
'segmentation/ade20k/ADE_val_00001142.jpg?raw=true'
filename = 'example.jpg'
img = gluoncvth.utils.load_image(
gluoncvth.utils.download(url, filename)).unsqueeze(0)
# Make prediction
output = model.evaluate(img)
predict = torch.max(output, 1)[1].cpu().numpy() + 1
# Get color pallete for visualization
mask = gluoncvth.utils.get_mask_pallete(predict, 'ade20k')
mask.save('output.png')
More models available at GluonCV Semantic Segmentation ModelZoo
API Reference
ResNet
gluoncvth.models.resnet18(pretrained=True)gluoncvth.models.resnet34(pretrained=True)gluoncvth.models.resnet50(pretrained=True)gluoncvth.models.resnet101(pretrained=True)gluoncvth.models.resnet152(pretrained=True)
FCN
gluoncvth.models.get_fcn_resnet101_voc(pretrained=True)gluoncvth.models.get_fcn_resnet101_ade(pretrained=True)
PSPNet
gluoncvth.models.get_psp_resnet101_voc(pretrained=True)gluoncvth.models.get_psp_resnet101_ade(pretrained=True)
DeepLabV3
gluoncvth.models.get_deeplab_resnet101_voc(pretrained=True)gluoncvth.models.get_deeplab_resnet101_ade(pretrained=True)
Why GluonCV?
1. State-of-the-art Implementations
2. Pretrained Models and Tutorials
3. Community Support
We expect this PyTorch inference API for GluonCV models will be beneficial to the entire computer vision comunity.
Metadata
Release files for gluoncv-torch 0.0.5
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| gluoncv-torch-0.0.5.tar.gz | 15.0 kB | Without provenance | Details for gluoncv-torch-0.0.5.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| gluoncv_torch-0.0.5-py3-none-any.whl | Python 3 | none | any | Details for gluoncv_torch-0.0.5-py3-none-any.whl |
Total release size: 36.0 kB
Release files / gluoncv-torch-0.0.5.tar.gz
| Download URL | gluoncv-torch-0.0.5.tar.gz |
|---|---|
| Size | 15.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
e428c509f0dfea6c04b0d51e2b57b2137be8368a2f10f480c5c898f1483d2cfc
|
|
BLAKE2b-256 checksum How to use checksums |
ab7117f6b94d70f584a4c425b5a19cba462ce5d64fbac1842f6c1004b6056212
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.2.0 pkginfo/1.5.0.1 requests/2.24.0 setuptools/41.2.0 requests-toolbelt/0.9.1 tqdm/4.46.1 CPython/3.7.7
|
Release files / gluoncv_torch-0.0.5-py3-none-any.whl
| Download URL | gluoncv_torch-0.0.5-py3-none-any.whl |
|---|---|
| Size | 21.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
1bea3ce72af2b102940e4e430e027574e1033f47863fe3e486cf833a2af3818f
|
|
BLAKE2b-256 checksum How to use checksums |
b64027ce0231f908ac79a1cab92a2dff33eebecdeaa4ad71be7d01424f4c294e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.2.0 pkginfo/1.5.0.1 requests/2.24.0 setuptools/41.2.0 requests-toolbelt/0.9.1 tqdm/4.46.1 CPython/3.7.7
|
Security for gluoncv-torch 0.0.5
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.