一、代码下载地址
GitHub - facebookresearch/mae: PyTorch implementation of MAE https//arxiv.org/abs/2111.06377
二、预训练模型下载地址
注意不是下面这个:
而是下面这个:
三、测试代码
在根目录下,建立demo.py文件,如下
import sys
import os
import requests
import torch
import numpy as np
import matplotlib
import matplotlib.pyplot as plt
matplotlib.use('TKAgg')
from PIL import Image
import models_mae
import os
os.environ["KMP_DUPLICATE_LIB_OK"]="TRUE"
# define the utils
imagenet_mean = np.array([0.485, 0.456, 0.406])
imagenet_std = np.array([0.229, 0.224, 0.225])
def show_image(image, title=''):
# image is [H, W, 3]
assert image.shape[2] == 3
plt.imshow(torch.clip((image * imagenet_std + imagenet_mean) * 255, 0, 255).int())
plt.title(title, fontsize=16)
plt.axis('off')
return
def prepare_model(chkpt_dir, arch='mae_vit_large_patch16'):
# build model
model = getattr(models_mae, arch)()
# load model
checkpoint = torch.load(chkpt_dir, map_location='cpu')
msg = model.load_state_dict(checkpoint['model'], strict=False)
print(msg)
return model
def run_one_image(img, model):
x = torch.tensor(img)
# make it a batch-like
x = x.unsqueeze(dim=0)
x = torch.einsum('nhwc->nchw', x)
# run MAE
loss, y, mask = model(x.float(), mask_ratio=0.75) # y是重构出的tokens
y = model.unpatchify(y)
y = torch.einsum('nchw->nhwc', y).detach().cpu()
# visualize the mask
mask = mask.detach()
mask = mask.unsqueeze(-1).repeat(1, 1, model.patch_embed.patch_size[0] ** 2 * 3) # (N, H*W, p*p*3)
mask = model.unpatchify(mask) # 1 is removing, 0 is keeping
mask = torch.einsum('nchw->nhwc', mask).detach().cpu()
x = torch.einsum('nchw->nhwc', x)
# masked image
im_masked = x * (1 - mask) # 掩盖75%后的原图
# MAE reconstruction pasted with visible patches
im_paste = x * (1 - mask) + y * mask # 25%原图+75%生成图
# make the plt figure larger
plt.rcParams['figure.figsize'] = [24, 24]
plt.subplot(1, 4, 1)
show_image(x[0], "original")
plt.subplot(1, 4, 2)
show_image(im_masked[0], "masked")
plt.subplot(1, 4, 3)
show_image(y[0], "reconstruction")
plt.subplot(1, 4, 4)
show_image(im_paste[0], "reconstruction + visible")
plt.show()
# load an image
img_path = '1.jpg'
# img = Image.open(requests.get(img_url, stream=True).raw)
img = Image.open(img_path)
img = img.resize((224, 224))
img = np.array(img) / 255.
assert img.shape == (224, 224, 3)
# normalize by ImageNet mean and std
img = img - imagenet_mean
img = img / imagenet_std
plt.rcParams['figure.figsize'] = [5, 5]
show_image(torch.tensor(img))
print('-------1')
# --------------------------mae_model-----------------------------
chkpt_dir = 'mae_visualize_vit_large.pth'
print('-------2')
model_mae = prepare_model(chkpt_dir, 'mae_vit_large_patch16')
print('-------3')
print('Model loaded.')
torch.manual_seed(2)
print('MAE with pixel reconstruction:')
run_one_image(img, model_mae)
# --------------------------mae_ganloss---------------------------
chkpt_dir = 'mae_visualize_vit_large_ganloss.pth'
model_mae_gan = prepare_model(chkpt_dir, 'mae_vit_large_patch16')
print('Model loaded.')
torch.manual_seed(2)
print('MAE with extra GAN loss:')
run_one_image(img, model_mae_gan)
注意,其中的
import os
os.environ["KMP_DUPLICATE_LIB_OK"]="TRUE"
是为了解决OMP: Hint This means that multiple copies of the OpenMP runtime have been linked into the program.我自己加的。
两个预训练模型,跟demo.py放在同一个文件夹下。
四、改一下models_mae.py
我把那个qk_scale=None删掉了