def show_prediction_channels(prediction_tensor):
channel_images = []
for chan in prediction_tensor:
z = np.zeros(chan.shape)
channel = np.stack([chan.cpu().detach().numpy(), z, z], axis=2)
channel_images.append(channel)
channels_images = np.array(channel_images)
display_all(channel_images)
labels = labels.to(device)
predictions = model(inputs)
metrics = defaultdict(float)
epoch_samples = inputs.size(0)
loss = calc_loss(predictions, labels, metrics)
print_metrics(metrics, epoch_samples, 'val')
predictions = F.sigmoid(predictions)
import helper
input_images = [tensor_to_np(x) for x in inputs]
mask_images = [helper.masks_to_colorimg(x) for x in labels]
prediction_images = [helper.masks_to_colorimg(x) for x in predictions]
chicken.display_all(input_images + mask_images + prediction_images)
def pred_to_channels(single_pred):
channel_images = []
# z = np.zeros(pix.shape)
for pix in single_pred:
z = np.zeros(pix.shape)
channel = np.stack([pix, z, z], axis=2)
channel_images.append(channel)
return np.array(channel_images)
channel_images = pred_to_channels(predictions[0])
def display_all(self, images, figs_per_page=20, titles=None):
images = chicken.squeeze(images)
images = chicken.data2d_to_grayscale(images)
chicken.display_all(images, figs_per_page, titles)
return