Skip to main content

JSB Framework

Project description

Semantic Segmentation and Edge Detection

Setup

# install mmcv and pytorch

# install other dependencies
pip install -r requirements.txt

# If you want to install potato globally
python setup.py develop

Datasets

python tools/convert_datasets/preprocess_cityscapes.py

Training

CUDA_VISIBLE_DEVICES=0,1 ./tools/dist_train.sh <path/to/config> <num_gpus>

Test

Evaluate and Visualize Segmentatation and Edges

CUDA_VISIBLE_DEVICES=0,1 ./tools/dist_train.sh <path/to/config> <path/to/ckpt> <num_gpus> ...

To evaluate F-boundary scores:

# only supports single gpu
CUDA_VISIBLE_DEVICES=0, python tools/test_boundary_fscore.py <path/to/config> <path/to/ckpt> ...

Evaluate Edges

# save edges
CUDA_VISIBLE_DEVICES=0,1 ./tools/dist_train.sh <path/to/config> <path/to/ckpt> <num_gpus> --save-edge ...

python tools/test_edge.py <path/to/config> <path/to/predictions> ...

Evaluating edges will take a very long time (depends on the hardware).

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

potato-cv-0.1.0.tar.gz (82.0 kB view details)

Uploaded Source

Built Distribution

potato_cv-0.1.0-py3-none-any.whl (122.4 kB view details)

Uploaded Python 3

File details

Details for the file potato-cv-0.1.0.tar.gz.

File metadata

  • Download URL: potato-cv-0.1.0.tar.gz
  • Upload date:
  • Size: 82.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.1 CPython/3.8.8

File hashes

Hashes for potato-cv-0.1.0.tar.gz
Algorithm Hash digest
SHA256 ec9caaffd079f4a026afb4a73caf3570d92310b1d248f87c40aa6c9070580ef8
MD5 71f04783e6dafb17a7be26794161b4ae
BLAKE2b-256 f8df3c330255aa4ab1eadeec51ea460e7815bab57cce574912173e25a1029b7e

See more details on using hashes here.

File details

Details for the file potato_cv-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: potato_cv-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 122.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.1 CPython/3.8.8

File hashes

Hashes for potato_cv-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 27dd34fc5411d7abe4b830be723bddd3fb340e1ef2007f6d6054dc98357868e5
MD5 bdd595dda83dc9f43fbb9b1fc63741e7
BLAKE2b-256 50448975d003dc8e4a9d111515533bdb9c67bc0f5d5c4668a41e7d21eacbe171

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page