ahirner / Pytorch Retraining
Licence: bsd-3-clause
Transfer Learning Shootout for PyTorch's model zoo (torchvision)
Stars: ✭ 167
Projects that are alternatives of or similar to Pytorch Retraining
Weakly Supervised 3d Object Detection
Weakly Supervised 3D Object Detection from Point Clouds (VS3D), ACM MM 2020
Stars: ✭ 61 (-63.47%)
Mutual labels: jupyter-notebook, transfer-learning
Intrusion Detection System Using Deep Learning
VGG-19 deep learning model trained using ISCX 2012 IDS Dataset
Stars: ✭ 85 (-49.1%)
Mutual labels: jupyter-notebook, transfer-learning
Sru Deeplearning Workshop
دوره 12 ساعته یادگیری عمیق با چارچوب Keras
Stars: ✭ 66 (-60.48%)
Mutual labels: jupyter-notebook, transfer-learning
Teacher Student Training
This repository stores the files used for my summer internship's work on "teacher-student learning", an experimental method for training deep neural networks using a trained teacher model.
Stars: ✭ 34 (-79.64%)
Mutual labels: jupyter-notebook, transfer-learning
Image classifier
CNN image classifier implemented in Keras Notebook 🖼️.
Stars: ✭ 139 (-16.77%)
Mutual labels: jupyter-notebook, transfer-learning
Average Word2vec
🔤 Calculate average word embeddings (word2vec) from documents for transfer learning
Stars: ✭ 52 (-68.86%)
Mutual labels: jupyter-notebook, transfer-learning
Imageclassification
Deep Learning: Image classification, feature visualization and transfer learning with Keras
Stars: ✭ 83 (-50.3%)
Mutual labels: jupyter-notebook, transfer-learning
Getting Things Done With Pytorch
Jupyter Notebook tutorials on solving real-world problems with Machine Learning & Deep Learning using PyTorch. Topics: Face detection with Detectron 2, Time Series anomaly detection with LSTM Autoencoders, Object Detection with YOLO v5, Build your first Neural Network, Time Series forecasting for Coronavirus daily cases, Sentiment Analysis with BERT.
Stars: ✭ 738 (+341.92%)
Mutual labels: jupyter-notebook, transfer-learning
Keras transfer cifar10
Object classification with CIFAR-10 using transfer learning
Stars: ✭ 120 (-28.14%)
Mutual labels: jupyter-notebook, transfer-learning
Dogbreed gluon
kaggle Dog Breed Identification
Stars: ✭ 116 (-30.54%)
Mutual labels: jupyter-notebook, transfer-learning
Densedepth
High Quality Monocular Depth Estimation via Transfer Learning
Stars: ✭ 963 (+476.65%)
Mutual labels: jupyter-notebook, transfer-learning
Image keras
Building an image classifier using keras
Stars: ✭ 162 (-2.99%)
Mutual labels: jupyter-notebook, transfer-learning
Seismic Transfer Learning
Deep-learning seismic facies on state-of-the-art CNN architectures
Stars: ✭ 32 (-80.84%)
Mutual labels: jupyter-notebook, transfer-learning
Neural Painters X
Neural Paiters
Stars: ✭ 61 (-63.47%)
Mutual labels: jupyter-notebook, transfer-learning
Skin Cancer Image Classification
Skin cancer classification using Inceptionv3
Stars: ✭ 16 (-90.42%)
Mutual labels: jupyter-notebook, transfer-learning
Tensorflow
This Repository contains all tensorflow tutorials.
Stars: ✭ 68 (-59.28%)
Mutual labels: jupyter-notebook, transfer-learning
Transfer Learning Library
Transfer-Learning-Library
Stars: ✭ 678 (+305.99%)
Mutual labels: transfer-learning, benchmark
Caffenet Benchmark
Evaluation of the CNN design choices performance on ImageNet-2012.
Stars: ✭ 700 (+319.16%)
Mutual labels: jupyter-notebook, benchmark
Tweet Stance Prediction
Applying NLP transfer learning techniques to predict Tweet stance
Stars: ✭ 91 (-45.51%)
Mutual labels: jupyter-notebook, transfer-learning
pytorch-retraining
Transfer Learning shootout for PyTorch's model zoo (torchvision).
- Load any pretrained model with custom final layer (num_classes) from PyTorch's model zoo in one line
model_pretrained, diff = load_model_merged('inception_v3', num_classes)
- Retrain minimal (as inferred on load) or a custom amount of layers on multiple GPUs. Optionally with Cyclical Learning Rate (Smith 2017).
final_param_names = [d[0] for d in diff]
stats = train_eval(model_pretrained, trainloader, testloader, final_params_names)
-
Chart
training_time,evaluation_time(fps), top-1accuracyfor varying levels of retraining depth (shallow, deep and from scratch)
 |
|---|
| Transfer learning on example dataset Bee vs Ants with 2xV100 GPUs |
Results on more elaborate Dataset
num_classes = 23, slightly unbalanced, high variance in rotation and motion blur artifacts with 1xGTX1080Ti
 |
|---|
| Constant LR with momentum |
 |
|---|
| Cyclical Learning Rate |
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].