A TensorFlow implementation of Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks (http://arxiv.org/pdf/1312.6082.pdf)
I trained the model using SVHN dataset and get around 80% accuracy on my own dataset. So I determine to finetune it on my dataset.
train_layers = ['hidden10', 'digit_length', 'digit1', 'digit2', 'digit3', 'digit4']
fine_tune_var_list = [v for v in tf.trainable_variables() if v.name.split('/')[0] in train_layers]
train_op = optimizer.minimize(loss, global_step=global_step, var_list=fine_tune_var_list)
I tried learning rate from 1e-2 to 1e-5 but the accuracy is always around 80% with loss around 1~2.
I wonder how to make it perform better?
I trained the model using SVHN dataset and get around 80% accuracy on my own dataset. So I determine to finetune it on my dataset.
I tried learning rate from 1e-2 to 1e-5 but the accuracy is always around 80% with loss around 1~2. I wonder how to make it perform better?