The prediction files in the "prediction" folder look like they are predicting all black images as the output, and I am not sure how I can fix it. Any advice?
Also I know that to change the optimizer I simply don Unet.trainer(net, optimizer = "Adam")
but how can I change the learning rate? I was a little confused about this part.
Hello,
I used the example code
https://tf-unet.readthedocs.io/en/latest/usage.html
`from tf_unet import unet, util, image_util
preparing data loading
data_provider = image_util.ImageDataProvider("train/*.png")
setup & training
net = unet.Unet(layers=3, features_root=64, channels=1, n_class=2) trainer = unet.Trainer(net) path = trainer.train(data_provider, "checkpoints", training_iters=32, epochs=100)
verification
...
prediction = net.predict(path, data)
unet.error_rate(prediction, util.crop_to_shape(label, prediction.shape))
img = util.combine_img_prediction(data, label, prediction) util.save_image(img, "prediction.jpg")`
The prediction files in the "prediction" folder look like they are predicting all black images as the output, and I am not sure how I can fix it. Any advice?
Also I know that to change the optimizer I simply don Unet.trainer(net, optimizer = "Adam")
but how can I change the learning rate? I was a little confused about this part.