konverner

def encode_onehot(labels: list):
    labels = np.array(labels)
    shape = (labels.size, labels.max()+1)
    one_hot = np.zeros(shape)
    rows = np.arange(labels.size)
    one_hot[rows, labels] = 1
    return one_hot

konverner

from IPython.display import FileLink
FileLink(PATH)

konverner

def show_img_grid(images, labels, N):
    n = int(N**(0.5))
    k = 0
    f, axarr = plt.subplots(n,n,figsize=(10,10))
    for i in range(n):
        for j in range(n):
            axarr[i,j].set_title(labels[k])
            axarr[i,j].imshow(images[k])
            k += 1

konverner

def count_parameters(model):
    return sum(p.numel() for p in model.parameters() if p.requires_grad)

konverner

konverner

ABCDEFGHIJKLMNOPQRSTUVWXYZfabcdefghijklmnopqrstuvwxyz

konverner

fig = plt.figure(figsize=(4,4))
ax = fig.add_subplot(111, projection='3d')
ax.scatter(df['Gene 1'], df['Gene 2'], df['Gene 3'])

konverner

fig, axs = plt.subplots(1, 2)
fig.set_figheight(4)
fig.set_figwidth(13)
axs[0].scatter(X1, Y1)
axs[1].scatter(X2, Y2)

axs[0].set_title("North")
axs[0].set_ylabel('mortality')
axs[0].set_xlabel('hardness')

konverner

seed = 42
torch.manual_seed(seed)
torch.cuda.manual_seed(seed)
np.random.seed(seed)
random.seed(seed)

konverner

class DataLoader:
    def __init__(self, dir):
        self.dir = dir
        self.filenames = [filename for filename in os.listdir(dir)]
        self.index = -1
        self.size = len(self.filenames)

    def __iter__(self):
        return self