model
"""
original code from facebook research:
https://github.com/facebookresearch/ConvNeXt
"""
import torch
import torch.nn as nn
import torch.nn.functional as F
def drop_path(x, drop_prob: float = 0., training: bool = False):
"""Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).
This is the same as the DropConnect impl I created for EfficientNet, etc networks, however,
the original name is misleading as 'Drop Connect' is a different form of dropout in a separate paper...
See discussion: https://github.com/tensorflow/tpu/issues/494#issuecomment-532968956 ... I've opted for
changing the layer and argument names to 'drop path' rather than mix DropConnect as a layer name and use
'survival rate' as the argument.
"""
if drop_prob == 0. or not training:
return x
keep_prob = 1 - drop_prob
shape = (x.shape[0],) + (1,) * (x.ndim - 1) # work with diff dim tensors, not just 2D ConvNets
random_tensor = keep_prob + torch.rand(shape, dtype=x.dtype, device=x.device)
random_tensor.floor_() # binarize
output = x.div(keep_prob) * random_tensor
return output
class DropPath(nn.Module):
"""Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).
"""
def __init__(self, drop_prob=None):
super(DropPath, self).__init__()
self.drop_prob = drop_prob
def forward(self, x):
return drop_path(x, self.drop_prob, self.training)
class LayerNorm(nn.Module):
r""" LayerNorm that supports two data formats: channels_last (default) or channels_first.
The ordering of the dimensions in the inputs. channels_last corresponds to inputs with
shape (batch_size, height, width, channels) while channels_first corresponds to inputs
with shape (batch_size, channels, height, width).
"""
def __init__(self, normalized_shape, eps=1e-6, data_format="channels_last"):
super().__init__()
self.weight = nn.Parameter(torch.ones(normalized_shape), requires_grad=True)
self.bias = nn.Parameter(torch.zeros(normalized_shape), requires_grad=True)
self.eps = eps
self.data_format = data_format
if self.data_format not in ["channels_last", "channels_first"]:
raise ValueError(f"not support data format '{self.data_format}'")
self.normalized_shape = (normalized_shape,)
def forward(self, x: torch.Tensor) -> torch.Tensor:
if self.data_format == "channels_last":
return F.layer_norm(x, self.normalized_shape, self.weight, self.bias, self.eps)
elif self.data_format == "channels_first":
# [batch_size, channels, height, width]
mean = x.mean(1, keepdim=True)
var = (x - mean).pow(2).mean(1, keepdim=True)
x = (x - mean) / torch.sqrt(var + self.eps)
x = self.weight[:, None, None] * x + self.bias[:, None, None]
return x
class Block(nn.Module):
r""" ConvNeXt Block. There are two equivalent implementations:
(1) DwConv -> LayerNorm (channels_first) -> 1x1 Conv -> GELU -> 1x1 Conv; all in (N, C, H, W)
(2) DwConv -> Permute to (N, H, W, C); LayerNorm (channels_last) -> Linear -> GELU -> Linear; Permute back
We use (2) as we find it slightly faster in PyTorch
Args:
dim (int): Number of input channels.
drop_rate (float): Stochastic depth rate. Default: 0.0
layer_scale_init_value (float): Init value for Layer Scale. Default: 1e-6.
"""
def __init__(self, dim, drop_rate=0., layer_scale_init_value=1e-6):
super().__init__()
self.dwconv = nn.Conv2d(dim, dim, kernel_size=7, padding=3, groups=dim) # depthwise conv
self.norm = LayerNorm(dim, eps=1e-6, data_format="channels_last")
self.pwconv1 = nn.Linear(dim, 4 * dim) # pointwise/1x1 convs, implemented with linear layers
self.act = nn.GELU()
self.pwconv2 = nn.Linear(4 * dim, dim)
self.gamma = nn.Parameter(layer_scale_init_value * torch.ones((dim,)),
requires_grad=True) if layer_scale_init_value > 0 else None
self.drop_path = DropPath(drop_rate) if drop_rate > 0. else nn.Identity()
def forward(self, x: torch.Tensor) -> torch.Tensor:
shortcut = x
x = self.dwconv(x)
x = x.permute(0, 2, 3, 1) # [N, C, H, W] -> [N, H, W, C]
x = self.norm(x)
x = self.pwconv1(x)
x = self.act(x)
x = self.pwconv2(x)
if self.gamma is not None:
x = self.gamma * x
x = x.permute(0, 3, 1, 2) # [N, H, W, C] -> [N, C, H, W]
x = shortcut + self.drop_path(x)
return x
class ConvNeXt(nn.Module):
r""" ConvNeXt
A PyTorch impl of : `A ConvNet for the 2020s` -
https://arxiv.org/pdf/2201.03545.pdf
Args:
in_chans (int): Number of input image channels. Default: 3
num_classes (int): Number of classes for classification head. Default: 1000
depths (tuple(int)): Number of blocks at each stage. Default: [3, 3, 9, 3]
dims (int): Feature dimension at each stage. Default: [96, 192, 384, 768]
drop_path_rate (float): Stochastic depth rate. Default: 0.
layer_scale_init_value (float): Init value for Layer Scale. Default: 1e-6.
head_init_scale (float): Init scaling value for classifier weights and biases. Default: 1.
"""
def __init__(self, in_chans: int = 3, num_classes: int = 1000, depths: list = None,
dims: list = None, drop_path_rate: float = 0., layer_scale_init_value: float = 1e-6,
head_init_scale: float = 1.):
super().__init__()
self.downsample_layers = nn.ModuleList() # stem and 3 intermediate downsampling conv layers
stem = nn.Sequential(nn.Conv2d(in_chans, dims[0], kernel_size=4, stride=4),
LayerNorm(dims[0], eps=1e-6, data_format="channels_first"))
self.downsample_layers.append(stem)
# 对应stage2-stage4前的3个downsample
for i in range(3):
downsample_layer = nn.Sequential(LayerNorm(dims[i], eps=1e-6, data_format="channels_first"),
nn.Conv2d(dims[i], dims[i+1], kernel_size=2, stride=2))
self.downsample_layers.append(downsample_layer)
self.stages = nn.ModuleList() # 4 feature resolution stages, each consisting of multiple blocks
dp_rates = [x.item() for x in torch.linspace(0, drop_path_rate, sum(depths))]
cur = 0
# 构建每个stage中堆叠的block
for i in range(4):
stage = nn.Sequential(
*[Block(dim=dims[i], drop_rate=dp_rates[cur + j], layer_scale_init_value=layer_scale_init_value)
for j in range(depths[i])]
)
self.stages.append(stage)
cur += depths[i]
self.norm = nn.LayerNorm(dims[-1], eps=1e-6) # final norm layer
self.head = nn.Linear(dims[-1], num_classes)
self.apply(self._init_weights)
self.head.weight.data.mul_(head_init_scale)
self.head.bias.data.mul_(head_init_scale)
def _init_weights(self, m):
if isinstance(m, (nn.Conv2d, nn.Linear)):
nn.init.trunc_normal_(m.weight, std=0.2)
nn.init.constant_(m.bias, 0)
def forward_features(self, x: torch.Tensor) -> torch.Tensor:
for i in range(4):
x = self.downsample_layers[i](x)
x = self.stages[i](x)
return self.norm(x.mean([-2, -1])) # global average pooling, (N, C, H, W) -> (N, C)
def forward(self, x: torch.Tensor) -> torch.Tensor:
x = self.forward_features(x)
x = self.head(x)
return x
def convnext_tiny(num_classes: int):
# https://dl.fbaipublicfiles.com/convnext/convnext_tiny_1k_224_ema.pth
model = ConvNeXt(depths=[3, 3, 9, 3],
dims=[96, 192, 384, 768],
num_classes=num_classes)
return model
def convnext_small(num_classes: int):
# https://dl.fbaipublicfiles.com/convnext/convnext_small_1k_224_ema.pth
model = ConvNeXt(depths=[3, 3, 27, 3],
dims=[96, 192, 384, 768],
num_classes=num_classes)
return model
def convnext_base(num_classes: int):
# https://dl.fbaipublicfiles.com/convnext/convnext_base_1k_224_ema.pth
# https://dl.fbaipublicfiles.com/convnext/convnext_base_22k_224.pth
model = ConvNeXt(depths=[3, 3, 27, 3],
dims=[128, 256, 512, 1024],
num_classes=num_classes)
return model
def convnext_large(num_classes: int):
# https://dl.fbaipublicfiles.com/convnext/convnext_large_1k_224_ema.pth
# https://dl.fbaipublicfiles.com/convnext/convnext_large_22k_224.pth
model = ConvNeXt(depths=[3, 3, 27, 3],
dims=[192, 384, 768, 1536],
num_classes=num_classes)
return model
def convnext_xlarge(num_classes: int):
# https://dl.fbaipublicfiles.com/convnext/convnext_xlarge_22k_224.pth
model = ConvNeXt(depths=[3, 3, 27, 3],
dims=[256, 512, 1024, 2048],
num_classes=num_classes)
return model
train
import os
import argparse
import torch
import torch.optim as optim
from torch.utils.tensorboard import SummaryWriter
from torchvision import transforms
from my_dataset import MyDataSet
from model import convnext_tiny as create_model
from utils import read_split_data, create_lr_scheduler, get_params_groups, train_one_epoch, evaluate
def main(args):
device = torch.device(args.device if torch.cuda.is_available() else "cpu")
print(f"using {device} device.")
if os.path.exists("./weights") is False:
os.makedirs("./weights")
tb_writer = SummaryWriter()
train_images_path, train_images_label, val_images_path, val_images_label = read_split_data(args.data_path)
img_size = 224
data_transform = {
"train": transforms.Compose([transforms.RandomResizedCrop(img_size),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])]),
"val": transforms.Compose([transforms.Resize(int(img_size * 1.143)),
transforms.CenterCrop(img_size),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])])}
# 实例化训练数据集
train_dataset = MyDataSet(images_path=train_images_path,
images_class=train_images_label,
transform=data_transform["train"])
# 实例化验证数据集
val_dataset = MyDataSet(images_path=val_images_path,
images_class=val_images_label,
transform=data_transform["val"])
batch_size = args.batch_size
#nw = min([os.cpu_count(), batch_size if batch_size > 1 else 0, 8]) # number of workers
nw=0
print('Using {} dataloader workers every process'.format(nw))
train_loader = torch.utils.data.DataLoader(train_dataset,
batch_size=batch_size,
shuffle=True,
pin_memory=True,
num_workers=nw,
collate_fn=train_dataset.collate_fn)
val_loader = torch.utils.data.DataLoader(val_dataset,
batch_size=batch_size,
shuffle=False,
pin_memory=True,
num_workers=nw,
collate_fn=val_dataset.collate_fn)
model = create_model(num_classes=args.num_classes).to(device)
if args.weights != "":
assert os.path.exists(args.weights), "weights file: '{}' not exist.".format(args.weights)
weights_dict = torch.load(args.weights, map_location=device)["model"]
# 删除有关分类类别的权重
for k in list(weights_dict.keys()):
if "head" in k:
del weights_dict[k]
print(model.load_state_dict(weights_dict, strict=False))
if args.freeze_layers:
for name, para in model.named_parameters():
# 除head外，其他权重全部冻结
if "head" not in name:
para.requires_grad_(False)
else:
print("training {}".format(name))
# pg = [p for p in model.parameters() if p.requires_grad]
pg = get_params_groups(model, weight_decay=args.wd)
optimizer = optim.AdamW(pg, lr=args.lr, weight_decay=args.wd)
lr_scheduler = create_lr_scheduler(optimizer, len(train_loader), args.epochs,
warmup=True, warmup_epochs=1)
best_acc = 0.
for epoch in range(args.epochs):
# train
train_loss, train_acc = train_one_epoch(model=model,
optimizer=optimizer,
data_loader=train_loader,
device=device,
epoch=epoch,
lr_scheduler=lr_scheduler)
# validate
val_loss, val_acc = evaluate(model=model,
data_loader=val_loader,
device=device,
epoch=epoch)
tags = ["train_loss", "train_acc", "val_loss", "val_acc", "learning_rate"]
tb_writer.add_scalar(tags[0], train_loss, epoch)
tb_writer.add_scalar(tags[1], train_acc, epoch)
tb_writer.add_scalar(tags[2], val_loss, epoch)
tb_writer.add_scalar(tags[3], val_acc, epoch)
tb_writer.add_scalar(tags[4], optimizer.param_groups[0]["lr"], epoch)
if best_acc < val_acc:
torch.save(model.state_dict(), "./weights/best_model.pth")
best_acc = val_acc
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--num_classes', type=int, default=5)
parser.add_argument('--epochs', type=int, default=1)
parser.add_argument('--batch-size', type=int, default=1)
parser.add_argument('--lr', type=float, default=5e-4)
parser.add_argument('--wd', type=float, default=5e-2)
# 数据集所在根目录
# https://storage.googleapis.com/download.tensorflow.org/example_images/flower_photos.tgz
parser.add_argument('--data-path', type=str,
default="F:/deep-learning-for-image-processing-master-pili/deep-learning-for-image-processing-master/data_set/flower_data/flower_photos")
# 预训练权重路径，如果不想载入就设置为空字符
# 链接: https://pan.baidu.com/s/1aNqQW4n_RrUlWUBNlaJRHA 密码: i83t
parser.add_argument('--weights', type=str, default='convnext_tiny_1k_224_ema.pth',
help='initial weights path')
# 是否冻结head以外所有权重
parser.add_argument('--freeze-layers', type=bool, default=False)
parser.add_argument('--device', default='cuda:0', help='device id (i.e. 0 or 0,1 or cpu)')
opt = parser.parse_args()
main(opt)
predict
import os
import json
import torch
from PIL import Image
from torchvision import transforms
import matplotlib.pyplot as plt
from model import convnext_tiny as create_model
def main():
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print(f"using {device} device.")
num_classes = 5
img_size = 224
data_transform = transforms.Compose(
[transforms.Resize(int(img_size * 1.14)),
transforms.CenterCrop(img_size),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])])
# load image
img_path = "1.jpg"
assert os.path.exists(img_path), "file: '{}' dose not exist.".format(img_path)
img = Image.open(img_path)
plt.imshow(img)
# [N, C, H, W]
img = data_transform(img)
# expand batch dimension
img = torch.unsqueeze(img, dim=0)
# read class_indict
json_path = './class_indices.json'
assert os.path.exists(json_path), "file: '{}' dose not exist.".format(json_path)
with open(json_path, "r") as f:
class_indict = json.load(f)
# create model
model = create_model(num_classes=num_classes).to(device)
# load model weights
model_weight_path = "weights/best_model.pth"
model.load_state_dict(torch.load(model_weight_path, map_location=device))
model.eval()
with torch.no_grad():
# predict class
output = torch.squeeze(model(img.to(device))).cpu()
predict = torch.softmax(output, dim=0)
predict_cla = torch.argmax(predict).numpy()
print_res = "class: {} prob: {:.3}".format(class_indict[str(predict_cla)],
predict[predict_cla].numpy())
plt.title(print_res)
for i in range(len(predict)):
print("class: {:10} prob: {:.3}".format(class_indict[str(i)],
predict[i].numpy()))
plt.show()
if __name__ == '__main__':
main()
预测一轮结果
来自
https://github.com/WZMIAOMIAO/deep-learning-for-image-processing
580
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
