{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import glob\nimport torch \nimport torch.nn as nn\nimport pandas as pd\nimport matplotlib.pyplot as plt\nimport cv2 \nfrom skimage import io, transform\nfrom torchvision.transforms import transforms\nfrom torchvision import utils\nimport numpy as np\nfrom torchvision import datasets\nfrom torch.utils.data import DataLoader, Dataset\nimport pandas as pd\nfrom tqdm import tqdm\nfrom sklearn import metrics\nfrom sklearn.metrics import f1_score, accuracy_score\nfrom sklearn.preprocessing import MultiLabelBinarizer\nimport os\nimport torchvision.models as models\ntest_fram = pd.read_csv('../input/plant-pathology-2021-fgvc8/sample_submission.csv')\ntest_fram.values[1][0]","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class LeafDataset(Dataset):\n    def __init__(self, csv_file, root_dir, transform):\n        self.train_fram = pd.read_csv(csv_file)\n        self.root_dir = root_dir\n        self.transform = transform\n    def __len__(self):\n        return len(self.train_fram)\n    def __getitem__(self, idx):\n        if torch.is_tensor(idx):\n            idx = idx.tolist()\n        img_name = os.path.join(self.root_dir, self.train_fram.values[idx][0])\n        image = cv2.imread(img_name)\n        labels = [1]\n        sample = {'image': image, 'labels': labels}\n        if self.transform :\n            sample = self.transform(sample)\n        return sample\nclass ToTensor(object):\n    def __call__(self, sample):\n        image = sample[\"image\"]\n        labels = sample[\"labels\"]\n        image = image.transpose((2,0,1))\n        return {\"image\" : torch.from_numpy(image),\n                \"labels\" : labels\n        }\nclass Rescale(object):\n\n    def __init__(self, output_size):\n        assert isinstance(output_size, (int, tuple))\n        self.output_size = output_size\n\n    def __call__(self, sample):\n        image, labels = sample['image'], sample['labels']\n\n        h, w = image.shape[:2]\n        if isinstance(self.output_size, int):\n            if h > w:\n                new_h, new_w = self.output_size * h / w, self.output_size\n            else:\n                new_h, new_w = self.output_size, self.output_size * w / h\n        else:\n            new_h, new_w = self.output_size\n\n        new_h, new_w = int(new_h), int(new_w)\n\n        img = transform.resize(image, (new_h, new_w))\n\n\n        return {'image': img, 'labels': labels}\n\n\nclass RandomCrop(object):\n\n    def __init__(self, output_size):\n        assert isinstance(output_size, (int, tuple))\n        if isinstance(output_size, int):\n            self.output_size = (output_size, output_size)\n        else:\n            assert len(output_size) == 2\n            self.output_size = output_size\n\n    def __call__(self, sample):\n        image, labels = sample['image'], sample['labels']\n\n        h, w = image.shape[:2]\n        new_h, new_w = self.output_size\n\n        top = np.random.randint(0, h - new_h)\n        left = np.random.randint(0, w - new_w)\n\n        image = image[top: top + new_h,\n                      left: left + new_w]\n\n        return {'image': image, 'labels': labels}\nleafDatasets = LeafDataset('../input/plant-pathology-2021-fgvc8/sample_submission.csv', '../input/plant-pathology-2021-fgvc8/test_images', transform=transforms.Compose([Rescale(256), RandomCrop(224), ToTensor()]))\nprint(leafDatasets[0])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"batch_size = 32\nnum_workers = 4\ntest_loader = DataLoader(leafDatasets, batch_size=batch_size, num_workers=num_workers)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"resnet = models.resnet152(pretrained=False)\nnum_ftrs = resnet.fc.in_features\nresnet.fc = nn.Linear(num_ftrs, 6)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"load_path = '../input/modelres/resnet.pkl'\nresnet.load_state_dict(torch.load(load_path))\nresnet","metadata":{"collapsed":true,"jupyter":{"outputs_hidden":true},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"resnet.to('cuda')\ndef to_numpy(tensor):\n    return tensor.detach().cpu().numpy() if tensor.requires_grad else tensor.cpu().numpy()\ny_pred_proba = np.empty(shape=(0, 6), dtype=np.int)\n\nstream = tqdm(test_loader)\nfor batch, sample in enumerate(stream):\n    X = sample['image']\n    X = X.float().to('cuda')\n    pred = to_numpy(resnet(X)) \n    y_pred_proba = np.vstack((y_pred_proba, pred))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"y_pred_proba\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"y_pred_proba = y_pred_proba.tolist()\nindices =  []\nfor pred in y_pred_proba:\n    temp = []\n    for category in pred:\n        if category >= 0:\n            print(category)\n            temp.append(pred.index(category))\n    if temp!=[]:\n        indices.append(temp)\n    else:\n        temp.append(np.argmax(pred))\n        indices.append(temp)\n    \n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"labels =  [\n        'complex','frog_eye_leaf_spot','healthy','powdery_mildew','rust','scab'\n    ]\ntestlabels = []\n\n\nfor image in indices:\n    temp = []\n    for i in image:\n        temp.append(str(labels[i]))\n    testlabels.append(' '.join(temp))\n\nprint(testlabels)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sub = pd.read_csv('../input/plant-pathology-2021-fgvc8/sample_submission.csv')\nsub['labels'] = testlabels\nsub.to_csv('submission.csv', index=False)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}