saliency
fsdl-text-recognizer-2022-labs
Our great sponsors
saliency | fsdl-text-recognizer-2022-labs | |
---|---|---|
4 | 1 | |
929 | 419 | |
0.8% | 3.6% | |
3.6 | 6.3 | |
about 1 month ago | 3 months ago | |
Jupyter Notebook | Jupyter Notebook | |
Apache License 2.0 | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
saliency
-
[D] Is the math in Integrated gradients (4K citations) wrong?
Found relevant code at https://github.com/PAIR-code/saliency + all code implementations here
- How to display which parts of a single image a Keras model found to be the most significant when making a prediction?
-
Gradients of model output layer and intermediate layer wrt inputs
I’m trying to visualize model layer outputs using the saliency core package package on a simple conv net. This requires me to compute the gradients of the model output layer and intermediate convolutional layer output w.r.t the input. I’ve attempted to do this in the last code block, but I run into the error
-
A Visual History of Interpretation for Image Recognition
[2]: https://github.com/PAIR-code/saliency
fsdl-text-recognizer-2022-labs
-
MLops Resources
full-stack-deep-learning
What are some alternatives?
gradio - Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!
Made-With-ML - Learn how to design, develop, deploy and iterate on production-grade ML applications.
EfficientWord-Net - OneShot Learning-based hotword detection.
Andrew-NG-Notes - This is Andrew NG Coursera Handwritten Notes.
yolov3-tf2 - YoloV3 Implemented in Tensorflow 2.0
learnopencv - Learn OpenCV : C++ and Python Examples
darkflow - Translate darknet to tensorflow. Load trained weights, retrain/fine-tune using tensorflow, export constant graph def to mobile devices
stock-prediction-deep-neural-learning - Predicting stock prices using a TensorFlow LSTM (long short-term memory) neural network for times series forecasting
Emotion_Detection_CNN_keras - Train and test our algorithm using Convolution Neural Networks and classify emotions in real-time.
docs - TensorFlow documentation
vision-camera-realtime-object-detection - VisionCamera Frame Processor Plugin to detect objects using TensorFlow Lite Task Vision
One-Piece-Image-Classifier - A quick image classifier trained with manually selected One Piece images.