Open xellDart opened 2 years ago
Hi, I train my model using keras, and I load data using this function
Resize the images to a fixed input size, and rescale the input channels to a range of [-1,1]
IMG_SIZE = 320 # All images will be resized to 160x160 def format_example(pair): image, label = pair['image'], pair['label'] image = tf.cast(image, tf.float32) image = (image/127.5) - 1 image = tf.image.resize(image, (IMG_SIZE, IMG_SIZE)) return image, label
But i cant understand what norm mean values apply when I transform my model to other framework, for example, ncnn, Pytorch use
But what value I need to apply in keras mobilenetv2 model?
Hi, I train my model using keras, and I load data using this function
Resize the images to a fixed input size, and rescale the input channels to a range of [-1,1]
But i cant understand what norm mean values apply when I transform my model to other framework, for example, ncnn, Pytorch use
But what value I need to apply in keras mobilenetv2 model?