jittor和pytorch对比
东方佑
世界500强企业,算法工程师,大模型设计,炼丹
展开
-
jittor和pytorch生成网络对比之unit
jittor代码import globimport randomimport osimport numpy as npfrom jittor.dataset.dataset import Datasetfrom PIL import Imageimport jittor.transform as transformclass ImageDataset(Dataset): def __init__(self, root, transforms_=None, unaligned=Fal原创 2021-01-04 12:52:21 · 448 阅读 · 0 评论 -
jittor和pytorch生成网络对比之wgan
jittor代码import jittor as jtfrom jittor import initfrom jittor import nnfrom jittor.dataset.mnist import MNISTimport jittor.transform as transformimport argparseimport osimport numpy as npimport mathimport sysimport cv2import timejt.flags.use原创 2021-01-04 12:51:44 · 326 阅读 · 0 评论 -
jittor和pytorch生成网络对比之wgan_div
jittor代码import argparseimport osimport numpy as npimport mathimport sysimport jittor as jtfrom jittor import nnos.makedirs("images", exist_ok=True)parser = argparse.ArgumentParser()parser.add_argument("--n_epochs", type=int, default=200, help="原创 2021-01-04 12:51:29 · 451 阅读 · 0 评论 -
jittor和pytorch生成网络对比之wgan_gp
jittor代码import jittor as jtfrom jittor import init,nnimport argparseimport osimport numpy as npimport mathimport sysfrom jittor.dataset.mnist import MNISTimport jittor.transform as transformimport cv2import timejt.flags.use_cuda = 1os.makedir原创 2021-01-04 12:51:08 · 442 阅读 · 0 评论 -
jittor和pytorch生成网络对比之stargan
jittor代码import globimport randomimport osimport numpy as npfrom jittor.dataset.dataset import Datasetimport jittor.transform as transformfrom PIL import Imageclass CelebADataset(Dataset): def __init__(self, root, transform_=None, mode="train"原创 2021-01-04 12:52:38 · 430 阅读 · 0 评论 -
jittor和pytorch生成网络对比之softmax_gan
jittor代码import jittor as jtfrom jittor import initfrom jittor import nnfrom jittor.dataset.mnist import MNISTimport jittor.transform as transformimport argparseimport osimport numpy as npimport mathimport cv2import timejt.flags.use_cuda = 1o原创 2021-01-03 19:41:34 · 383 阅读 · 0 评论 -
jittor和pytorch生成网络对比之sgan
jittor代码import argparseimport osimport numpy as npimport mathos.makedirs("images", exist_ok=True)parser = argparse.ArgumentParser()parser.add_argument("--n_epochs", type=int, default=200, help="number of epochs of training")parser.add_argument("--原创 2021-01-03 19:39:20 · 515 阅读 · 0 评论 -
jittor和pytorch生成网络对比之relativistic_gan
jittor代码import argparseimport osimport numpy as npimport mathimport mnistmfrom jittor.dataset.mnist import MNISTimport jittor.transform as transformimport jittor as jtfrom jittor import initfrom jittor import nnjt.flags.use_cuda = 1os.makedirs原创 2021-01-03 19:37:17 · 490 阅读 · 0 评论 -
jittor和pytorch生成网络对比之pixelda
jittor代码from __future__ import print_functionimport errnoimport osimport picklefrom jittor.dataset.dataset import Datasetfrom PIL import Imageclass MNISTM(Dataset): """`MNIST-M Dataset.""" def __init__(self, mnist_root="data", train=True原创 2021-01-03 19:32:34 · 396 阅读 · 0 评论 -
jittor和pytorch生成网络对比之pix2pix
jittor 代码import globimport randomimport osimport numpy as npfrom jittor.dataset.dataset import Datasetimport jittor.transform as transformfrom PIL import Imageclass ImageDataset(Dataset): def __init__(self, root, transforms_=None, mode="train原创 2021-01-03 19:29:57 · 403 阅读 · 0 评论 -
jittor和pytorch生成网络对比之gan
jittor代码import argparseimport osimport numpy as npimport mathos.makedirs("images/static/", exist_ok=True)os.makedirs("images/varying_c1/", exist_ok=True)os.makedirs("images/varying_c2/", exist_ok=True)parser = argparse.ArgumentParser()parser.add原创 2021-01-03 19:26:46 · 354 阅读 · 0 评论 -
jittor和pytorch生成网络对比之gan
jittor代码import jittor as jtfrom jittor import initfrom jittor import nnfrom jittor.dataset.mnist import MNISTimport jittor.transform as transformimport argparseimport osimport numpy as npimport mathimport timeimport cv2jt.flags.use_cuda = 1o原创 2021-01-03 19:23:02 · 307 阅读 · 0 评论 -
jittor和pytorch生成网络对比之esrgan
jittor代码import globimport randomimport osimport numpy as npfrom jittor.dataset.dataset import Datasetfrom PIL import Imageimport jittor.transform as transformimport jittor as jtmean = np.array([0.485, 0.456, 0.406])std = np.array([0.229, 0.224,原创 2021-01-03 17:45:52 · 438 阅读 · 2 评论 -
jittor和pytorch生成网络对比之ebgan
pytorch代码import argparseimport osimport numpy as npimport mathimport torchvision.transforms as transformsfrom torchvision.utils import save_imagefrom torch.utils.data import DataLoaderfrom torchvision import datasetsfrom torch.autograd import Va原创 2021-01-03 17:38:13 · 379 阅读 · 0 评论 -
jittor拟合sin函数
import numpy as npimport matplotlib.pyplot as pltimport jittor as jtx_tensor = np.linspace(0, 6*np.pi, 10000) #创建一个输入数据集,[0-6*pi]x_data = jt.unsqueeze(jt.float(x_tensor), dim=1) #增加维度,将x的形状从[10000]变成二维[10000,1]y_data = np.sin(x_data.原创 2021-01-03 17:23:54 · 465 阅读 · 0 评论 -
jittor和pytorch生成网络对比之dragan
pytorch代码import argparseimport osimport numpy as npimport mathimport torchvision.transforms as transformsfrom torchvision.utils import save_imagefrom torch.utils.data import DataLoaderfrom torchvision import datasetsfrom torch.autograd import Va原创 2020-12-22 21:12:22 · 419 阅读 · 0 评论 -
jittor和pytorch生成网络对比之dcgan
pytorch代码import argparseimport osimport numpy as npimport mathimport torchvision.transforms as transformsfrom torchvision.utils import save_imagefrom torch.utils.data import DataLoaderfrom torchvision import datasetsfrom torch.autograd import Va原创 2020-12-22 21:10:29 · 304 阅读 · 0 评论 -
jittor和pytorch生成网络对比之cyclegan
pytorch代码import argparseimport osimport numpy as npimport mathimport itertoolsimport datetimeimport timeimport torchvision.transforms as transformsfrom torchvision.utils import save_image, make_gridfrom torch.utils.data import DataLoaderfrom t原创 2020-12-22 21:08:05 · 393 阅读 · 0 评论 -
jittor和pytorch网络对比之context_encoder
pytorch 代码"""Inpainting using Generative Adversarial Networks.The dataset can be downloaded from: https://www.dropbox.com/sh/8oqt9vytwxb3s4r/AADIKlz8PR9zr6Y20qbkunrba/Img/img_align_celeba.zip?dl=0(if not available there see if options are listed at htt原创 2020-12-22 21:03:35 · 517 阅读 · 0 评论 -
jittor和pytorch 生成网络对比之clustergan
pytorch代码from __future__ import print_functiontry: import argparse import os import numpy as np from torch.autograd import Variable from torch.autograd import grad as torch_grad import torch import torchvision impor原创 2020-12-22 20:59:11 · 494 阅读 · 3 评论 -
jittor和pytorch生成网络对比之cogan
pytorch代码import argparseimport osimport numpy as npimport mathimport scipyimport itertoolsimport mnistmimport torchvision.transforms as transformsfrom torchvision.utils import save_imagefrom torch.utils.data import DataLoaderfrom torchvision原创 2020-12-20 23:17:43 · 405 阅读 · 0 评论 -
jittor和pytorch生成网络对比之cgan
jittor代码import jittor as jtfrom jittor import initimport argparseimport osimport numpy as npimport mathfrom jittor import nnif jt.has_cuda: jt.flags.use_cuda = 1parser = argparse.ArgumentParser()parser.add_argument('--n_epochs', type=int,原创 2020-12-20 23:11:53 · 444 阅读 · 0 评论 -
jittor和pytorch生成网络对比之bicyclegan
pytorch代码import argparseimport osimport numpy as npimport mathimport itertoolsimport datetimeimport timeimport sysimport torchvision.transforms as transformsfrom torchvision.utils import save_imagefrom torch.utils.data import DataLoaderfrom t原创 2020-12-20 23:08:43 · 448 阅读 · 0 评论 -
jittor和pytorch生成网络对比之bggan
jittor代码import jittor as jtfrom jittor import initfrom jittor import nnfrom jittor.dataset.mnist import MNISTimport jittor.transform as transformimport argparseimport osimport numpy as npimport mathimport cv2import timejt.flags.use_cuda = 1o原创 2020-12-20 22:44:45 · 326 阅读 · 0 评论 -
jittor和pytorch生成网络对比之began
pytorch代码import argparseimport osimport numpy as npimport mathimport torchvision.transforms as transformsfrom torchvision.utils import save_imagefrom torch.utils.data import DataLoaderfrom torchvision import datasetsfrom torch.autograd import Va原创 2020-12-20 22:35:00 · 340 阅读 · 1 评论 -
jittor和pytorch生成网络对比之acgan
jittor 代码import jittor as jtfrom jittor import initfrom jittor import nnfrom jittor.dataset.mnist import MNISTimport jittor.transform as transformimport argparseimport os, sysimport numpy as npimport mathimport cv2import timeimport randomjt.原创 2020-12-20 22:32:28 · 727 阅读 · 0 评论 -
jittor 和pytorch的生成网络对比之aae
进行两个框架实际代码的对比工作原创 2020-12-20 17:24:26 · 455 阅读 · 0 评论