CornerNet | Update : please check out CornerNet-Lite

by princeton-vl Python Version: Current License: BSD-3-Clause

X-Ray Key Features Code Snippets(5)Community Discussions Vulnerabilities Install Support

kandi X-RAY | CornerNet Summary

CornerNet is a Python library. CornerNet has no bugs, it has no vulnerabilities, it has a Permissive License and it has medium support. However CornerNet build file is not available. You can download it from GitHub.

Update (4/18/2019): please check out CornerNet-Lite, more efficient variants of CornerNet.

Support

Quality

Security

License

Reuse

Support

CornerNet has a medium active ecosystem.

It has 2213 star(s) with 462 fork(s). There are 62 watchers for this library.

It had no major release in the last 6 months.

There are 125 open issues and 48 have been closed. On average issues are closed in 45 days. There are 4 open pull requests and 0 closed requests.

It has a neutral sentiment in the developer community.

The latest version of CornerNet is current.

Quality

CornerNet has no bugs reported.

Security

CornerNet has no vulnerabilities reported, and its dependent libraries have no vulnerabilities reported.

License

CornerNet is licensed under the BSD-3-Clause License. This license is Permissive.

Permissive licenses have the least restrictions, and you can use them in most projects.

Reuse

CornerNet releases are not available. You will need to build from source code and install.

CornerNet has no build file. You will be need to create the build yourself to build the component from source.

Installation instructions, examples and code snippets are available.

Top functions reviewed by kandi - BETA

kandi has reviewed CornerNet and discovered the below as its top functions. This is intended to give you an instant insight into CornerNet implemented functionality, and help decide if they suit your requirements.

KP detection
Shuffle the indices
Return the path to an image file
Return the detections at the given index
Train the model
Load pretrained model
Save the current state of the model
Load model parameters from cache file
Compute the train function
Gather features
Evaluate the cross - correlation
Helper function to decode heatmaps
Helper function for parallel_apply
Scatter
Convert inputs to kwargs
Load detections from the cache file
Extract data from the COCO image
Forward computation
Parse command line arguments
Perform a forward computation
Evaluate the model
Get data from queue

Get all kandi verified functions for this library.

CornerNet Key Features

No Key Features are available at this moment for CornerNet.

CornerNet Examples and Code Snippets

ExtremeNet 训练和测试,1.安装环境

Python

Lines of Code : 20

License : Permissive (BSD-3-Clause)

Copy

# No Anaconda 
pip3 install virtualenv 
# 创建python3虚拟环境
virtualenv -p python3 ExtremeNet
# 进入虚拟环境
source ExtremeNet/bin/activate
pip3 install -r requirement.txt -i https://pypi.tuna.tsinghua.edu.cn/simple
# 退出虚拟环境
deactivate


# Anaconda
# 创建虚拟环境并安装p

CornerNet-Lite

Python

Lines of Code : 15

License : No License

Copy

{
    "system": {
        "dataset": "VOC",
         ...
         "categories": x,  #x is your dataset categories
}

tl_heats = nn.ModuleList([self._pred_mod(X) for _ in range(stacks)])   #x is your dataset categories
br_heats = nn.ModuleList([self._

Compiling Corner Pooling Layers

Python

Lines of Code : 2

License : No License

Copy

cd /models/py_utils/_cpools/
python setup.py install --user

Calculate the loss of the loss function .

python

Lines of Code : 26

License : Permissive (MIT License)

Copy

def _neg_loss(pred, gt):
  ''' Modified focal loss. Exactly the same as CornerNet.
      Runs faster and costs a little bit more memory
    Arguments:
      pred (batch x c x h x w)
      gt_regr (batch x c x h x w)
  '''
  pos_inds = gt.eq(1).float(

Compute negative loss .

python

Lines of Code : 23

License : Permissive (MIT License)

Copy

def _slow_neg_loss(pred, gt):
  '''focal loss from CornerNet'''
  pos_inds = gt.eq(1)
  neg_inds = gt.lt(1)

  neg_weights = torch.pow(1 - gt[neg_inds], 4)

  loss = 0
  pos_pred = pred[pos_inds]
  neg_pred = pred[neg_inds]

  pos_loss = torch.log(po

Community Discussions

No Community Discussions are available at this moment for CornerNet.Refer to stack overflow page for discussions.

Community Discussions, Code Snippets contain sources that include Stack Exchange Network

Vulnerabilities

No vulnerabilities reported

Install CornerNet

Please first install Anaconda and create an Anaconda environment using the provided package list. After you create the environment, activate it. Our current implementation only supports GPU so you need a GPU and need to have CUDA installed on your machine.

Support

For any new features, suggestions and bugs create an issue on GitHub. If you have any questions check and ask questions on community page Stack Overflow .

Find more information at: