jxcodetw

# draw a bunch of samples
def random_walk(png, Gs, cx, cy, cw, ch, step, seeds):
    print(png)
    latents = np.stack(np.random.RandomState(seed).randn(Gs.input_shape[1]) for seed in seeds)
#     images = Gs.run(latents, None, **synthesis_kwargs) # [seed, y, x, rgb]
    
    idx = 0
    for idxx, (l1, l2) in enumerate(zip(latents, latents[1:])):
        print(idxx, '/', len(latents))
        latent = np.stack([l1 * (1-alpha) + l2 * alpha for alpha in np.linspace(0, 1, step)])

jxcodetw

{
    "lkunrate": [
      {
        "startDate": "2002-03-11",
        "endDate": "2002-08-26",
        "light": 1,
      },
      {
        "startDate": "2002-09-02",
        "endDate": "2002-12-02",

jxcodetw

import torch
import torch.optim as optim
import torch.nn as nn
import torch.nn.functional as F
from openTSNE import TSNE
import numpy as np
import matplotlib.pyplot as plt
from sklearn.manifold import SpectralEmbedding
from scipy.sparse import save_npz, load_npz
import random

jxcodetw

import torch
import torch.optim as optim
import torch.nn.functional as F
from openTSNE import TSNE
from umap.umap_ import fuzzy_simplicial_set, find_ab_params
import numpy as np
import matplotlib.pyplot as plt
from sklearn.manifold import SpectralEmbedding
from scipy.sparse import save_npz, load_npz
import random

jxcodetw

import torch
import torch.optim as optim
import torch.nn as nn
import torch.nn.functional as F
from umap.umap_ import fuzzy_simplicial_set, find_ab_params
import numpy as np
import matplotlib.pyplot as plt
from sklearn.manifold import SpectralEmbedding
from scipy.sparse import save_npz, load_npz
import random

jxcodetw

import torch
import torch.optim as optim
import torch.nn as nn
import torch.nn.functional as F
from openTSNE import TSNE
import numpy as np
import matplotlib.pyplot as plt
from sklearn.manifold import SpectralEmbedding
from scipy.sparse import save_npz, load_npz
from functools import partial