@@ -36,27 +36,13 @@ Classes are chair & kitchen & knife & saucepan. Classes are equal(1300 glass - 1
3636
3737Download pure data from [ here] ( https://www.kaggle.com/mbkinaci/chair-kitchen-knife-saucepan ) . Warning 962 MB.
3838
39- # CPU or GPU
40- I trained on GTX 1050. 1 epoch lasted 35 seconds approximately.
41- 42- If you are using CPU, which I do not recommend, change the lines below:
43- ```
44- config = tf.ConfigProto(allow_soft_placement=True)
45- config.gpu_options.allow_growth = True
46- config.gpu_options.allocator_type = 'BFC'
47- with tf.Session(config=config) as sess:
48- ```
49- to
50- ```
51- with tf.Session() as sess:
52- ```
5339# Architecture
5440
5541AlexNet is used as architecture. 5 convolution layers and 3 Fully Connected Layers with 0.5 Dropout Ratio. 60 million Parameters.
5642![ alt text] ( https://github.com/MuhammedBuyukkinaci/TensorFlow-Image-Classification-Convolutional-Neural-Networks/blob/master/alexnet_architecture.png )
5743
5844# Results
59- Accuracy score reached 89 % on CV after 30 epochs. Test accuracy is around 88% .
45+ Accuracy score reached 87 % on CV after just 5 epochs .
6046![ alt text] ( https://github.com/MuhammedBuyukkinaci/TensorFlow-Multiclass-Image-Classification-using-CNN-s/blob/master/mc_results.png )
6147
6248# Predictions
0 commit comments