gsurma / Image_classifier
Licence: mit
CNN image classifier implemented in Keras Notebook 🖼️.
Stars: ✭ 139
Programming Languages
python
139335 projects - #7 most used programming language
Labels
Projects that are alternatives of or similar to Image classifier
Artificio
Deep Learning Computer Vision Algorithms for Real-World Use
Stars: ✭ 326 (+134.53%)
Mutual labels: artificial-intelligence, ai, convolutional-neural-networks, image-classification, transfer-learning, image-recognition
Transfer Learning Suite
Transfer Learning Suite in Keras. Perform transfer learning using any built-in Keras image classification model easily!
Stars: ✭ 212 (+52.52%)
Mutual labels: artificial-intelligence, convolutional-neural-networks, cnn, image-classification, transfer-learning, image-recognition
Keras transfer cifar10
Object classification with CIFAR-10 using transfer learning
Stars: ✭ 120 (-13.67%)
Mutual labels: jupyter-notebook, convolutional-neural-networks, cnn, image-classification, transfer-learning, cnn-keras
Iresnet
Improved Residual Networks (https://arxiv.org/pdf/2004.04989.pdf)
Stars: ✭ 163 (+17.27%)
Mutual labels: artificial-intelligence, convolutional-neural-networks, cnn, image-classification, image-recognition
Deep Learning With Python
Deep learning codes and projects using Python
Stars: ✭ 195 (+40.29%)
Mutual labels: artificial-intelligence, jupyter-notebook, convolutional-neural-networks, cnn, image-classification
Imodels
Interpretable ML package 🔍 for concise, transparent, and accurate predictive modeling (sklearn-compatible).
Stars: ✭ 194 (+39.57%)
Mutual labels: artificial-intelligence, ai, jupyter-notebook, ml
Style transfer
CNN image style transfer 🎨.
Stars: ✭ 210 (+51.08%)
Mutual labels: jupyter-notebook, notebook, convolutional-neural-networks, cnn
Pyconv
Pyramidal Convolution: Rethinking Convolutional Neural Networks for Visual Recognition (https://arxiv.org/pdf/2006.11538.pdf)
Stars: ✭ 231 (+66.19%)
Mutual labels: artificial-intelligence, convolutional-neural-networks, cnn, image-recognition
Deeppicar
Deep Learning Autonomous Car based on Raspberry Pi, SunFounder PiCar-V Kit, TensorFlow, and Google's EdgeTPU Co-Processor
Stars: ✭ 242 (+74.1%)
Mutual labels: artificial-intelligence, jupyter-notebook, convolutional-neural-networks, transfer-learning
Polyaxon
Machine Learning Platform for Kubernetes (MLOps tools for experimentation and automation)
Stars: ✭ 2,966 (+2033.81%)
Mutual labels: artificial-intelligence, ai, notebook, ml
Pytorch Image Classification
Tutorials on how to implement a few key architectures for image classification using PyTorch and TorchVision.
Stars: ✭ 272 (+95.68%)
Mutual labels: jupyter-notebook, convolutional-neural-networks, cnn, image-classification
Awesome Ai Ml Dl
Awesome Artificial Intelligence, Machine Learning and Deep Learning as we learn it. Study notes and a curated list of awesome resources of such topics.
Stars: ✭ 831 (+497.84%)
Mutual labels: artificial-intelligence, ai, jupyter-notebook, ml
Nlpaug
Data augmentation for NLP
Stars: ✭ 2,761 (+1886.33%)
Mutual labels: artificial-intelligence, ai, jupyter-notebook, ml
Pba
Efficient Learning of Augmentation Policy Schedules
Stars: ✭ 461 (+231.65%)
Mutual labels: artificial-intelligence, jupyter-notebook, convolutional-neural-networks, image-classification
Deep learning projects
Stars: ✭ 28 (-79.86%)
Mutual labels: jupyter-notebook, convolutional-neural-networks, image-classification, image-recognition
Human Activity Recognition Using Cnn
Convolutional Neural Network for Human Activity Recognition in Tensorflow
Stars: ✭ 382 (+174.82%)
Mutual labels: jupyter-notebook, notebook, convolutional-neural-networks, cnn
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 (-75.54%)
Mutual labels: ai, jupyter-notebook, convolutional-neural-networks, transfer-learning
Computervision Recipes
Best Practices, code samples, and documentation for Computer Vision.
Stars: ✭ 8,214 (+5809.35%)
Mutual labels: artificial-intelligence, jupyter-notebook, convolutional-neural-networks, image-classification
Sru Deeplearning Workshop
دوره 12 ساعته یادگیری عمیق با چارچوب Keras
Stars: ✭ 66 (-52.52%)
Mutual labels: jupyter-notebook, convolutional-neural-networks, transfer-learning
Gtsrb
Convolutional Neural Network for German Traffic Sign Recognition Benchmark
Stars: ✭ 65 (-53.24%)
Mutual labels: jupyter-notebook, convolutional-neural-networks, cnn
Image Classifier
Python Jupyter Notebook with Convolutional Neural Network image classifier implemented in Keras 🖼️. It's Google Colab ready.
Check out corresponding Medium article:
Usage
Structure your data as follows:
data/
training/
class_a/
class_a01.jpg
class_a02.jpg
...
class_b/
class_b01.jpg
class_b02.jpg
...
validation/
class_a/
class_a01.jpg
class_a02.jpg
...
class_b/
class_b01.jpg
class_b02.jpg
...
For binary classifications you are good to go!
For non-binary classifications:
- add other classes to training and validation directories
- change class_mode from "binary" to "categorical"
- change loss function from "binary_crossentropy" to "categorical_crossentropy"
Performance
Dataset: Dogs vs Cats
Description: Binary classification. Two classes two distinguish - dogs and cats.
Training: 10 000 images per class
Validation: 2 500 images per class
model_1
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv2d_5 (Conv2D) (None, 198, 198, 32) 896
_________________________________________________________________
activation_9 (Activation) (None, 198, 198, 32) 0
_________________________________________________________________
max_pooling2d_5 (MaxPooling2 (None, 99, 99, 32) 0
_________________________________________________________________
conv2d_6 (Conv2D) (None, 97, 97, 32) 9248
_________________________________________________________________
activation_10 (Activation) (None, 97, 97, 32) 0
_________________________________________________________________
max_pooling2d_6 (MaxPooling2 (None, 48, 48, 32) 0
_________________________________________________________________
flatten_3 (Flatten) (None, 73728) 0
_________________________________________________________________
dense_5 (Dense) (None, 16) 1179664
_________________________________________________________________
activation_11 (Activation) (None, 16) 0
_________________________________________________________________
dropout_3 (Dropout) (None, 16) 0
_________________________________________________________________
dense_6 (Dense) (None, 1) 17
_________________________________________________________________
activation_12 (Activation) (None, 1) 0
=================================================================
Total params: 1,189,825
Trainable params: 1,189,825
Non-trainable params: 0
_________________________________________________________________
model_2
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv2d_4 (Conv2D) (None, 198, 198, 32) 896
_________________________________________________________________
activation_6 (Activation) (None, 198, 198, 32) 0
_________________________________________________________________
max_pooling2d_4 (MaxPooling2 (None, 99, 99, 32) 0
_________________________________________________________________
conv2d_5 (Conv2D) (None, 97, 97, 32) 9248
_________________________________________________________________
activation_7 (Activation) (None, 97, 97, 32) 0
_________________________________________________________________
max_pooling2d_5 (MaxPooling2 (None, 48, 48, 32) 0
_________________________________________________________________
conv2d_6 (Conv2D) (None, 46, 46, 64) 18496
_________________________________________________________________
activation_8 (Activation) (None, 46, 46, 64) 0
_________________________________________________________________
max_pooling2d_6 (MaxPooling2 (None, 23, 23, 64) 0
_________________________________________________________________
flatten_2 (Flatten) (None, 33856) 0
_________________________________________________________________
dense_3 (Dense) (None, 64) 2166848
_________________________________________________________________
activation_9 (Activation) (None, 64) 0
_________________________________________________________________
dropout_2 (Dropout) (None, 64) 0
_________________________________________________________________
dense_4 (Dense) (None, 1) 65
_________________________________________________________________
activation_10 (Activation) (None, 1) 0
=================================================================
Total params: 2,195,553
Trainable params: 2,195,553
Non-trainable params: 0
_________________________________________________________________
model_3
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv2d_4 (Conv2D) (None, 198, 198, 32) 896
_________________________________________________________________
activation_6 (Activation) (None, 198, 198, 32) 0
_________________________________________________________________
max_pooling2d_4 (MaxPooling2 (None, 99, 99, 32) 0
_________________________________________________________________
conv2d_5 (Conv2D) (None, 97, 97, 64) 18496
_________________________________________________________________
activation_7 (Activation) (None, 97, 97, 64) 0
_________________________________________________________________
max_pooling2d_5 (MaxPooling2 (None, 48, 48, 64) 0
_________________________________________________________________
conv2d_6 (Conv2D) (None, 46, 46, 128) 73856
_________________________________________________________________
activation_8 (Activation) (None, 46, 46, 128) 0
_________________________________________________________________
max_pooling2d_6 (MaxPooling2 (None, 23, 23, 128) 0
_________________________________________________________________
flatten_2 (Flatten) (None, 67712) 0
_________________________________________________________________
dense_3 (Dense) (None, 64) 4333632
_________________________________________________________________
activation_9 (Activation) (None, 64) 0
_________________________________________________________________
dropout_2 (Dropout) (None, 64) 0
_________________________________________________________________
dense_4 (Dense) (None, 1) 65
_________________________________________________________________
activation_10 (Activation) (None, 1) 0
=================================================================
Total params: 4,426,945
Trainable params: 4,426,945
Non-trainable params: 0
_________________________________________________________________
model_4
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv2d_7 (Conv2D) (None, 198, 198, 32) 896
_________________________________________________________________
activation_11 (Activation) (None, 198, 198, 32) 0
_________________________________________________________________
max_pooling2d_7 (MaxPooling2 (None, 99, 99, 32) 0
_________________________________________________________________
conv2d_8 (Conv2D) (None, 97, 97, 64) 18496
_________________________________________________________________
activation_12 (Activation) (None, 97, 97, 64) 0
_________________________________________________________________
max_pooling2d_8 (MaxPooling2 (None, 48, 48, 64) 0
_________________________________________________________________
conv2d_9 (Conv2D) (None, 46, 46, 128) 73856
_________________________________________________________________
activation_13 (Activation) (None, 46, 46, 128) 0
_________________________________________________________________
max_pooling2d_9 (MaxPooling2 (None, 23, 23, 128) 0
_________________________________________________________________
flatten_3 (Flatten) (None, 67712) 0
_________________________________________________________________
dense_5 (Dense) (None, 128) 8667264
_________________________________________________________________
activation_14 (Activation) (None, 128) 0
_________________________________________________________________
dropout_3 (Dropout) (None, 128) 0
_________________________________________________________________
dense_6 (Dense) (None, 1) 129
_________________________________________________________________
activation_15 (Activation) (None, 1) 0
=================================================================
Total params: 8,760,641
Trainable params: 8,760,641
Non-trainable params: 0
_________________________________________________________________
model_5
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv2d_1 (Conv2D) (None, 200, 200, 32) 896
_________________________________________________________________
conv2d_2 (Conv2D) (None, 200, 200, 32) 9248
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 100, 100, 32) 0
_________________________________________________________________
conv2d_3 (Conv2D) (None, 100, 100, 64) 18496
_________________________________________________________________
conv2d_4 (Conv2D) (None, 100, 100, 64) 36928
_________________________________________________________________
max_pooling2d_2 (MaxPooling2 (None, 50, 50, 64) 0
_________________________________________________________________
conv2d_5 (Conv2D) (None, 50, 50, 128) 73856
_________________________________________________________________
conv2d_6 (Conv2D) (None, 50, 50, 128) 147584
_________________________________________________________________
max_pooling2d_3 (MaxPooling2 (None, 25, 25, 128) 0
_________________________________________________________________
conv2d_7 (Conv2D) (None, 25, 25, 256) 295168
_________________________________________________________________
conv2d_8 (Conv2D) (None, 25, 25, 256) 590080
_________________________________________________________________
max_pooling2d_4 (MaxPooling2 (None, 12, 12, 256) 0
_________________________________________________________________
flatten_1 (Flatten) (None, 36864) 0
_________________________________________________________________
dense_1 (Dense) (None, 256) 9437440
_________________________________________________________________
dropout_1 (Dropout) (None, 256) 0
_________________________________________________________________
dense_2 (Dense) (None, 256) 65792
_________________________________________________________________
dropout_2 (Dropout) (None, 256) 0
_________________________________________________________________
dense_3 (Dense) (None, 1) 257
_________________________________________________________________
activation_1 (Activation) (None, 1) 0
=================================================================
Total params: 10,675,745
Trainable params: 10,675,745
Non-trainable params: 0
_________________________________________________________________
Author
Greg (Grzegorz) Surma
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].