通过timm下载模型

160 阅读 0 评论 106 点赞

我是靠谱客的博主平淡纸鹤，这篇文章主要介绍通过timm下载模型，现在分享给大家，希望可以做个参考。

import os
import warnings
from pprint import pprint
from glob import glob
from tqdm import tqdm

import torch
import torch.optim as optim
import torch.nn as nn
import torch.nn.functional as F
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import torchvision.transforms as T
from box import Box
from timm import create_model
from sklearn.model_selection import StratifiedKFold
from torchvision.io import read_image
from torch.utils.data import DataLoader, Dataset
from pytorch_grad_cam import GradCAMPlusPlus
from pytorch_grad_cam.utils.image import show_cam_on_image


import pytorch_lightning as pl
from pytorch_lightning.utilities.seed import seed_everything
from pytorch_lightning import callbacks
from pytorch_lightning.callbacks.progress import ProgressBarBase
from pytorch_lightning.callbacks.early_stopping import EarlyStopping
from pytorch_lightning.loggers import TensorBoardLogger
from pytorch_lightning import LightningDataModule, LightningModule

config = {'seed': 20211111,
          'root': './input/petfinder-pawpularity-score/', 
          'n_splits': 5,
          'epoch': 60,
          'trainer': {
              'gpus': 1,
              'accumulate_grad_batches': 1,
              'progress_bar_refresh_rate': 1,
              'fast_dev_run': False,
              'num_sanity_val_steps': 0,
              'resume_from_checkpoint': None,
          },
          'transform':{
              'name': 'get_default_transforms',
              'image_size': 600
          },
          'train_loader':{
              'batch_size': 2,
              'shuffle': True,
              'num_workers': 4,
              'pin_memory': False,
              'drop_last': True,
          },
          'val_loader': {
              'batch_size': 2,
              'shuffle': False,
              'num_workers': 4,
              'pin_memory': False,
              'drop_last': False
         },
          'model':{
              'name': 'vit_large_patch16_384',
              'output_dim': 1
          },
          'optimizer':{
              'name': 'optim.AdamW',
              'params':{
                  'lr': 1e-5
              },
          },
          'scheduler':{
              'name': 'optim.lr_scheduler.CosineAnnealingWarmRestarts',
              'params':{
                  'T_0': 20,
                  'eta_min': 1e-4,
              }
          },
          'loss': 'nn.BCEWithLogitsLoss',
}
config = Box(config)
pprint(config)


class Model(pl.LightningModule):
    def __init__(self, cfg):
        super().__init__()
        self.cfg = cfg
        self.__build_model()
        self._criterion = eval(self.cfg.loss)()
        self.transform = get_default_transforms()
        self.save_hyperparameters(cfg)

    def __build_model(self):
        self.backbone = create_model(
            self.cfg.model.name, pretrained=True, num_classes=0, in_chans=3
        )
        num_features = self.backbone.num_features
        self.fc = nn.Sequential(
            nn.Dropout(0.5), nn.Linear(num_features, self.cfg.model.output_dim)
        )

    def forward(self, x):
        f = self.backbone(x)
        out = self.fc(f)
        return out

    def training_step(self, batch, batch_idx):
        loss, pred, labels = self.__share_step(batch, 'train')
        return {'loss': loss, 'pred': pred, 'labels': labels}
        
    def validation_step(self, batch, batch_idx):
        loss, pred, labels = self.__share_step(batch, 'val')
        return {'pred': pred, 'labels': labels}
    
    def __share_step(self, batch, mode):
        images, labels = batch
        labels = labels.float() / 100.0
        images = self.transform[mode](images)
        
        if torch.rand(1)[0] < 0.5 and mode == 'train':
            mix_images, target_a, target_b, lam = mixup(images, labels, alpha=0.5)
            logits = self.forward(mix_images).squeeze(1)
            loss = self._criterion(logits, target_a) * lam + 
                (1 - lam) * self._criterion(logits, target_b)
        else:
            logits = self.forward(images).squeeze(1)
            loss = self._criterion(logits, labels)
        
        pred = logits.sigmoid().detach().cpu() * 100.
        labels = labels.detach().cpu() * 100.
        return loss, pred, labels
        
    def training_epoch_end(self, outputs):
        self.__share_epoch_end(outputs, 'train')

    def validation_epoch_end(self, outputs):
        self.__share_epoch_end(outputs, 'val')    
        
    def __share_epoch_end(self, outputs, mode):
        preds = []
        labels = []
        for out in outputs:
            pred, label = out['pred'], out['labels']
            preds.append(pred)
            labels.append(label)
        preds = torch.cat(preds)
        labels = torch.cat(labels)
        metrics = torch.sqrt(((labels - preds) ** 2).mean())
        self.log(f'{mode}_loss', metrics)
    
    def check_gradcam(self, dataloader, target_layer, target_category, reshape_transform=None):
        cam = GradCAMPlusPlus(
            model=self,
            #target_layer=target_layer, 
            target_layers=[target_layer], 
            use_cuda=self.cfg.trainer.gpus, 
            reshape_transform=reshape_transform)
        
        org_images, labels = iter(dataloader).next()
        cam.batch_size = len(org_images)
        images = self.transform['val'](org_images)
        images = images.to(self.device)
        logits = self.forward(images).squeeze(1)
        pred = logits.sigmoid().detach().cpu().numpy() * 100
        labels = labels.cpu().numpy()
        
        grayscale_cam = cam(input_tensor=images, target_category=target_category, eigen_smooth=True)
        org_images = org_images.detach().cpu().numpy().transpose(0, 2, 3, 1) / 255.
        return org_images, grayscale_cam, pred, labels

    def configure_optimizers(self):
        optimizer = eval(self.cfg.optimizer.name)(
            self.parameters(), **self.cfg.optimizer.params
        )
        scheduler = eval(self.cfg.scheduler.name)(
            optimizer,
            **self.cfg.scheduler.params
        )
        return [optimizer], [scheduler]

IMAGENET_MEAN = [0.485, 0.456, 0.406]  # RGB
IMAGENET_STD = [0.229, 0.224, 0.225]  # RGB
def get_default_transforms():
    transform = {
        "train": T.Compose(
            [
                T.RandomHorizontalFlip(),
                T.RandomVerticalFlip(),
                T.RandomAffine(15, translate=(0.1, 0.1), scale=(0.9, 1.1)),
                T.ColorJitter(brightness=0.1, contrast=0.1, saturation=0.1),
                T.ConvertImageDtype(torch.float),
                T.Normalize(mean=IMAGENET_MEAN, std=IMAGENET_STD),
            ]
        ),
        "val": T.Compose(
            [
                T.ConvertImageDtype(torch.float),
                T.Normalize(mean=IMAGENET_MEAN, std=IMAGENET_STD),
            ]
        ),
    }
    return transform

model = Model(config)