Comments (3)
Example from PYPI page for PYTORCHCV
from pytorchcv.model_provider import get_model as ptcv_get_model
import torch
from torch.autograd import Variable
net = ptcv_get_model("resnet18", pretrained=True, num_classes=200)
x = Variable(torch.randn(1, 3, 224, 224))
y = net(x)
from caltech_birds.
Call is get_model method with network name as argument, like TIMM.
Can also pass kwargs num_classes=200 to change the output linear classifier layer to the number of classes of the problem at hand.
from caltech_birds.
Added and shown to be working, committed to models_dev branch.
from caltech_birds.
Related Issues (20)
- Add support for more loss criterion to Trainer class.
- Add inference methods to Trainer class. HOT 1
- Investigate Ignite training scripts and successfully train a few models. HOT 1
- Create Trainer class for Ignite framework. HOT 2
- Investigate Lightning training scripts and train a few models.
- Refactor main script to use Trainer class which takes care of all model related objects and commence training. HOT 1
- Use config file to control model parameters so that single training scripts can be used, with new Trainer class. HOT 1
- Take Torchvision model selection code out of Trainer init method and write separate private method which is called from init method. HOT 2
- Integrate torchmetrics package for all metrics used. HOT 1
- Add Trainer class for Ignite models. HOT 5
- Ignite events, logging and callbacks controlled via configuration file
- Add support for all Torchvision models HOT 1
- Investigate deploying training of models via ClearML platform for model and data versioning. HOT 1
- Write config YAMLs for all models trained so far. HOT 1
- Modify setup.py so that it has entry points for CLI application added. HOT 1
- Move Torchscript conversion function into the IgniteTrainer class and reference from the ClearMLIgniteTrainer class to keep ClearML and general useful utilities separate. HOT 3
- Make command line argument configuration overrides work by using ARGS module in CUB_TOOLS package
- get_parser() overrides config file to a default file if none is given on execution HOT 1
- setup.py dependencies need updating
- EARLY_STOPPING_PATIENCE config keyword sitting in wrong place in config.py HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from caltech_birds.