0bserver07 / Keras Segnet Basic
Licence: mit
SegNet-Basic with Keras
Stars: ✭ 80
Labels
Projects that are alternatives of or similar to Keras Segnet Basic
Probabilistic Programming
Experimenting with and teaching probabilistic programming
Stars: ✭ 80 (+0%)
Mutual labels: jupyter-notebook
Visual tracking api
A simple visual tracking interface using Python
Stars: ✭ 80 (+0%)
Mutual labels: jupyter-notebook
Kdd20 Hands On Tutorial
Scalable Graph Neural Networks with Deep Graph Library
Stars: ✭ 80 (+0%)
Mutual labels: jupyter-notebook
Peregrine
Peregrine: Fast Genome Assembler Using SHIMMER Index
Stars: ✭ 80 (+0%)
Mutual labels: jupyter-notebook
Trumania
Trumania is a scenario-based random dataset generator library in python 3
Stars: ✭ 79 (-1.25%)
Mutual labels: jupyter-notebook
Exportify
Export Spotify playlists using the Web API. Analyze them in the Jupyter notebook.
Stars: ✭ 80 (+0%)
Mutual labels: jupyter-notebook
Fraud Detection Using Machine Learning
Setup end to end demo architecture for predicting fraud events with Machine Learning using Amazon SageMaker
Stars: ✭ 80 (+0%)
Mutual labels: jupyter-notebook
Multi Label Text Classification
Kaggle Toxic Comments Challenge
Stars: ✭ 80 (+0%)
Mutual labels: jupyter-notebook
Ismir2020 Metric Learning
ISMIR 2020 Tutorial for Metric Learning in MIR
Stars: ✭ 80 (+0%)
Mutual labels: jupyter-notebook
Alice
NIPS 2017: ALICE: Towards Understanding Adversarial Learning for Joint Distribution Matching
Stars: ✭ 80 (+0%)
Mutual labels: jupyter-notebook
Introstatlearn
Exercises from 'Introduction to Statistical Learning with Applications in R' written in Python.
Stars: ✭ 79 (-1.25%)
Mutual labels: jupyter-notebook
Quantum machine learning live
This is the code for "Quantum Machine Learning LIVE" By Siraj Raval on Youtube
Stars: ✭ 80 (+0%)
Mutual labels: jupyter-notebook
Tensorflow object detector
Tensorflow Object Detector
Stars: ✭ 80 (+0%)
Mutual labels: jupyter-notebook
Opam tip2018
Source code of our TIP 2018 paper "Object-Part Attention Model for Fine-grained Image Classification"
Stars: ✭ 80 (+0%)
Mutual labels: jupyter-notebook
SegNet-Basic:
What is Segnet?
- Deep Convolutional Encoder-Decoder Architecture for Semantic Pixel-wise Image Segmentation
Segnet = (Encoder + Decoder) + Pixel-Wise Classification layer
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation (Vijay Badrinarayanan, Alex Kendall, Roberto Cipolla, Senior Member, IEEE) arXiv:1511.00561v3
What is SegNet-Basic?
- "In order to analyse SegNet and compare its performance with FCN (decoder variants) we use a smaller version of SegNet, termed SegNet-Basic , which ha 4 encoders and 4 decoders. All the encoders in SegNet-Basic perform max-pooling and subsampling and the corresponding decoders upsample its input using the received max-pooling indices."
Basically it's a mini-segnet to experiment / test the architecure with convnets, such as FCN.
Steps To Run The Model:
-
Run
python model-basic.py
to createsegNet_basic_model
for keras to use.-
model-basic.py
contains the architecure.
-
Dataset:
-
In a different directory run this to download the dataset from original Implementation.
git clone [email protected]:alexgkendall/SegNet-Tutorial.git
- copy the
/CamVid
to here, or change theDataPath
indata_loader.py
to the above directory
-
The run
python data_loader.py
to generate these two files:-
/data/train_data.npz/
and/data/train_label.npz
- This will make it easy to process the model over and over, rather than waiting the data to be loaded into memory.
-
To Do:
[x] SegNet-Basic
[ ] SegNet
[x] Test Accuracy
[ ] Requirements
Segnet-Basic Road Scene Results:
- Train / Test:
Train on 367 samples, validate on 233 samples
Epoch 101/102
366/367 [============================>.]
- ETA: 0s - loss: 0.3835 - acc: 0.8737Epoch 00000: val_acc improved from -inf to 0.76367, saving model to weights.best.hdf5
367/367 [==============================]
- 231s - loss: 0.3832 - acc: 0.8738 - val_loss: 0.7655 - val_acc: 0.7637
Epoch 102/102
366/367 [============================>.]
- ETA: 0s - loss: 0.3589 - acc: 0.8809Epoch 00001: val_acc did not improve
367/367 [==============================]
- 231s - loss: 0.3586 - acc: 0.8810 - val_loss: 2.4447 - val_acc: 0.4478
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].