import os import time import math import random import numpy as np import pandas as pd from pathlib import Path import glob import matplotlib.pyplot as plt from PIL import Image, ImageEnhance, ImageOps from tqdm import tqdm, tqdm_notebook import torch from torch import nn, cuda from torch.autograd import Variable import torch.nn.functional as F import torchvision as vision import torchvision.models as models from torch.utils.data import Dataset, DataLoader from torch.optim import Adam, SGD, Optimizer from torch.optim.lr_scheduler import _LRScheduler, CosineAnnealingLR, ReduceLROnPlateau from sklearn.metrics import f1_score class CIFAR10Policy(object): """ Randomly choose one of the best 25 Sub-policies on CIFAR10. Example: >>> policy = CIFAR10Policy() >>> transformed = policy(image) Example as a PyTorch Transform: >>> transform=transforms.Compose([ >>> transforms.Resize(256), >>> CIFAR10Policy(), >>> transforms.ToTensor()]) """ def __init__(self, fillcolor=(128, 128, 128)): self.policies = [ SubPolicy(0.1, "invert", 7, 0.2, "contrast", 6, fillcolor), SubPolicy(0.7, "rotate", 2, 0.3, "translateX", 9, fillcolor), SubPolicy(0.8, "sharpness", 1, 0.9, "sharpness", 3, fillcolor), SubPolicy(0.5, "shearY", 8, 0.7, "translateY", 9, fillcolor), SubPolicy(0.5, "autocontrast", 8, 0.9, "equalize", 2, fillcolor), SubPolicy(0.2, "shearY", 7, 0.3, "posterize", 7, fillcolor), SubPolicy(0.4, "color", 3, 0.6, "brightness", 7, fillcolor), SubPolicy(0.3, "sharpness", 9, 0.7, "brightness", 9, fillcolor), SubPolicy(0.6, "equalize", 5, 0.5, "equalize", 1, fillcolor), SubPolicy(0.6, "contrast", 7, 0.6, "sharpness", 5, fillcolor), SubPolicy(0.7, "color", 7, 0.5, "translateX", 8, fillcolor), SubPolicy(0.3, "equalize", 7, 0.4, "autocontrast", 8, fillcolor), SubPolicy(0.4, "translateY", 3, 0.2, "sharpness", 6, fillcolor), SubPolicy(0.9, "brightness", 6, 0.2, "color", 8, fillcolor), SubPolicy(0.5, "solarize", 2, 0.0, "invert", 3, fillcolor), SubPolicy(0.2, "equalize", 0, 0.6, "autocontrast", 0, fillcolor), SubPolicy(0.2, "equalize", 8, 0.8, "equalize", 4, fillcolor), SubPolicy(0.9, "color", 9, 0.6, "equalize", 6, fillcolor), SubPolicy(0.8, "autocontrast", 4, 0.2, "solarize", 8, fillcolor), SubPolicy(0.1, "brightness", 3, 0.7, "color", 0, fillcolor), SubPolicy(0.4, "solarize", 5, 0.9, "autocontrast", 3, fillcolor), SubPolicy(0.9, "translateY", 9, 0.7, "translateY", 9, fillcolor), SubPolicy(0.9, "autocontrast", 2, 0.8, "solarize", 3, fillcolor), SubPolicy(0.8, "equalize", 8, 0.1, "invert", 3, fillcolor), SubPolicy(0.7, "translateY", 9, 0.9, "autocontrast", 1, fillcolor) ] def __call__(self, img): policy_idx = random.randint(0, len(self.policies) - 1) return self.policies[policy_idx](img) def __repr__(self): return "AutoAugment CIFAR10 Policy" class SubPolicy(object): def __init__(self, p1, operation1, magnitude_idx1, p2, operation2, magnitude_idx2, fillcolor=(128, 128, 128)): ranges = { "shearX": np.linspace(0, 0.3, 10), "shearY": np.linspace(0, 0.3, 10), "translateX": np.linspace(0, 150 / 331, 10), "translateY": np.linspace(0, 150 / 331, 10), "rotate": np.linspace(0, 30, 10), "color": np.linspace(0.0, 0.9, 10), "posterize": np.round(np.linspace(8, 4, 10), 0).astype(np.int), "solarize": np.linspace(256, 0, 10), "contrast": np.linspace(0.0, 0.9, 10), "sharpness": np.linspace(0.0, 0.9, 10), "brightness": np.linspace(0.0, 0.9, 10), "autocontrast": [0] * 10, "equalize": [0] * 10, "invert": [0] * 10 } # from https://stackoverflow.com/questions/5252170/specify-image-filling-color-when-rotating-in-python-with-pil-and-setting-expand def rotate_with_fill(img, magnitude): rot = img.convert("RGBA").rotate(magnitude) return Image.composite(rot, Image.new("RGBA", rot.size, (128,) * 4), rot).convert(img.mode) func = { "shearX": lambda img, magnitude: img.transform( img.size, Image.AFFINE, (1, magnitude * random.choice([-1, 1]), 0, 0, 1, 0), Image.BICUBIC, fillcolor=fillcolor), "shearY": lambda img, magnitude: img.transform( img.size, Image.AFFINE, (1, 0, 0, magnitude * random.choice([-1, 1]), 1, 0), Image.BICUBIC, fillcolor=fillcolor), "translateX": lambda img, magnitude: img.transform( img.size, Image.AFFINE, (1, 0, magnitude * img.size[0] * random.choice([-1, 1]), 0, 1, 0), fillcolor=fillcolor), "translateY": lambda img, magnitude: img.transform( img.size, Image.AFFINE, (1, 0, 0, 0, 1, magnitude * img.size[1] * random.choice([-1, 1])), fillcolor=fillcolor), "rotate": lambda img, magnitude: rotate_with_fill(img, magnitude), # "rotate": lambda img, magnitude: img.rotate(magnitude * random.choice([-1, 1])), "color": lambda img, magnitude: ImageEnhance.Color(img).enhance(1 + magnitude * random.choice([-1, 1])), "posterize": lambda img, magnitude: ImageOps.posterize(img, magnitude), "solarize": lambda img, magnitude: ImageOps.solarize(img, magnitude), "contrast": lambda img, magnitude: ImageEnhance.Contrast(img).enhance( 1 + magnitude * random.choice([-1, 1])), "sharpness": lambda img, magnitude: ImageEnhance.Sharpness(img).enhance( 1 + magnitude * random.choice([-1, 1])), "brightness": lambda img, magnitude: ImageEnhance.Brightness(img).enhance( 1 + magnitude * random.choice([-1, 1])), "autocontrast": lambda img, magnitude: ImageOps.autocontrast(img), "equalize": lambda img, magnitude: ImageOps.equalize(img), "invert": lambda img, magnitude: ImageOps.invert(img) } # self.name = "{}_{:.2f}_and_{}_{:.2f}".format( # operation1, ranges[operation1][magnitude_idx1], # operation2, ranges[operation2][magnitude_idx2]) self.p1 = p1 self.operation1 = func[operation1] self.magnitude1 = ranges[operation1][magnitude_idx1] self.p2 = p2 self.operation2 = func[operation2] self.magnitude2 = ranges[operation2][magnitude_idx2] def __call__(self, img): if random.random() < self.p1: img = self.operation1(img, self.magnitude1) if random.random() < self.p2: img = self.operation2(img, self.magnitude2) return img class TestDataset(Dataset): def __init__(self, df, mode='test', transforms=None): self.df = df self.mode = mode self.transform = transforms[self.mode] def __len__(self): return len(self.df) def __getitem__(self, idx): image = Image.open(TEST_IMAGE_PATH / self.df[idx]).convert("RGB") if self.transform: image = self.transform(image) return image target_size = (224, 224) data_transforms = { 'test': vision.transforms.Compose([ vision.transforms.Resize((224,224)), #vision.transforms.RandomResizedCrop(target_size, scale=(0.8,1.0)), #vision.transforms.RandomHorizontalFlip(), #vision.transforms.RandomRotation(20), #CIFAR10Policy(), vision.transforms.ToTensor(), vision.transforms.Normalize( [0.485, 0.456, 0.406], [0.229, 0.224, 0.225]) ]), } def seed_everything(seed): random.seed(seed) os.environ['PYTHONHASHSEED'] = str(seed) np.random.seed(seed) torch.manual_seed(seed) torch.cuda.manual_seed(seed) torch.backends.cudnn.deterministic = True SEED = 2019 seed_everything(SEED) def get_base_model(base_model, num_classes): if(base_model == 'ResNet-50' or base_model == 'fResNet-50' or base_model == 'gResNet-50'): model_ft = models.resnet50() model_ft.fc = nn.Linear(2048, num_classes) return model_ft, (224, 224) elif(base_model == 'ResNext50' or base_model == 'aResNext50' or base_model == 'bResNext50' or base_model == 'hResNext50'): model_ft = models.resnext50_32x4d() num_ftrs = model_ft.fc.in_features model_ft.fc = nn.Linear(num_ftrs, num_classes) return model_ft, (224, 224) elif(base_model == 'ResNext101' or base_model == 'fResNext101' or base_model == 'aResNext101' or base_model == 'cResNext101' or base_model == 'dResNext101'): model_ft = models.resnext101_32x8d() num_ftrs = model_ft.fc.in_features model_ft.fc = nn.Linear(num_ftrs, num_classes) return model_ft, (224, 224) elif(base_model == 'ResNet-101'): model_ft = models.resnet101() num_ftrs = model_ft.fc.in_features model_ft.fc = nn.Linear(num_ftrs, num_classes) return model_ft, (224, 224) elif(base_model == 'VGG19-bn'): model_ft = models.vgg19_bn() num_ftrs = model_ft.classifier[6].in_features model_ft.classifier[6] = nn.Linear(num_ftrs, num_classes) return model_ft, (224, 224) elif(base_model == 'aResNext101_32x8d_wsl' or base_model == 'bResNext101_32x8d_wsl' or base_model == 'cResNext101_32x8d_wsl'): model_ft = models.resnext101_32x8d() num_ftrs = model_ft.fc.in_features model_ft.fc = nn.Linear(num_ftrs, num_classes) return model_ft, (224, 224) elif(base_model == 'aResNext101_32x16d_wsl'): model_ft = torch.hub.load('facebookresearch/WSL-Images', 'resnext101_32x16d_wsl') num_ftrs = model_ft.fc.in_features model_ft.fc = nn.Linear(num_ftrs, num_classes) return model_ft, (224, 224) TEST_IMAGE_PATH = Path('../input/3rd-ml-month-car-image-cropping-dataset/test_crop/') test_csv = pd.read_csv('../input/2019-3rd-ml-month-with-kakr/test.csv') x_test = test_csv['img_file'] #target_models = ['bResNext50', 'aResNext50', 'cResNext101','fResNet-50', 'gResNet-50'] #target_folders = ['../input/bresnext50/', '../input/aresnext50/', '../input/cresnext101/', '../input/fresnet50/', '../input/gresnet50/'] #num_folder = [8, 4, 4, 4, 8] #target_models = ['bResNext50', 'cResNext101', 'fResNet-50', 'gResNet-50'] #target_folders = ['../input/bresnext50/', '../input/cresnext101/', '../input/fresnet50/', '../input/gresnet50/'] #num_folder = [8, 4, 4, 8] #target_models = ['bResNext50', 'aResNext50'] #target_folders = ['../input/bresnext50/', '../input/aresnext50/'] #target_models = ['bResNext50', 'aResNext50'] #target_folders = ['../input/bresnext50/', '../input/aresnext50/'] target_models = ['aResNext50', 'cResNext101_32x8d_wsl', 'bResNext101_32x8d_wsl', 'aResNext101_32x8d_wsl'] target_folders = ['../input/aresnext50/', '../input/cresnext101-32x8d-wsl/', '../input/bresnext101-32x8d-wsl/', '../input/aresnext101-32x8d-wsl/'] num_folder = [4, 12, 8, 4] print(os.listdir('../input')) #weights_paths = '../input/aresnext101/' #weights_path = '../input/4f_weights/' num_classes = 196 batch_size = 1 # 배치 1로 주면 순서대로 나온다 test_dataset = TestDataset(x_test, mode='test', transforms=data_transforms) test_loader = DataLoader(test_dataset, batch_size=batch_size, shuffle=False) # n_fold = 4 tta = 1 all_prediction = np.zeros((len(test_dataset), num_classes)) for k, target_model in enumerate(target_models): print(target_model) model, _ = get_base_model(target_model, num_classes) model.cuda() n_fold = num_folder[k] weights_path = target_folders[k] for i in range(n_fold): # print('{}th fold'.format(i)) path = weights_path + target_model + '_weight_best_{}.pt'.format(i) print(path) model.load_state_dict(torch.load(path)) model.eval() for _ in range(tta): print("tta {}".format(_+1)) prediction = np.zeros((len(test_dataset), num_classes)) # num_classes=196 with torch.no_grad(): for i, images in enumerate(test_loader): images = images.cuda() preds = model(images).detach() prediction[i * batch_size: (i+1) * batch_size] = preds.cpu().numpy() all_prediction = all_prediction + prediction total_fold = np.sum(num_folder) * tta #all_prediction /= (len(target_models) * n_fold * tta) all_prediction /= total_fold result = np.argmax(all_prediction, axis=1) submission = pd.read_csv('../input/2019-3rd-ml-month-with-kakr/sample_submission.csv') submission["class"] = result submission["class"].replace(0, 196, inplace=True) submission.to_csv("submission.csv", index=False) submission.head()