{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.14","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":3649,"databundleVersionId":46718,"sourceType":"competition"}],"dockerImageVersionId":30786,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"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","execution":{"iopub.status.busy":"2024-10-12T15:25:02.271181Z","iopub.execute_input":"2024-10-12T15:25:02.271675Z","iopub.status.idle":"2024-10-12T15:25:02.279919Z","shell.execute_reply.started":"2024-10-12T15:25:02.271635Z","shell.execute_reply":"2024-10-12T15:25:02.27866Z"},"trusted":true},"execution_count":2,"outputs":[{"name":"stdout","text":"/kaggle/input/cifar-10/trainLabels.csv\n/kaggle/input/cifar-10/sampleSubmission.csv\n/kaggle/input/cifar-10/test.7z\n/kaggle/input/cifar-10/train.7z\n","output_type":"stream"}]},{"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nfrom tqdm import tqdm\nfrom PIL import Image\n\nimport torch\nimport torch.nn as nn\nfrom torch.utils.data import Dataset, DataLoader\nimport torchvision.datasets as datasets\nfrom torchvision.models import resnet50\nfrom torchvision import transforms\nimport math","metadata":{"execution":{"iopub.status.busy":"2024-10-12T15:25:08.824301Z","iopub.execute_input":"2024-10-12T15:25:08.824722Z","iopub.status.idle":"2024-10-12T15:25:08.833881Z","shell.execute_reply.started":"2024-10-12T15:25:08.824681Z","shell.execute_reply":"2024-10-12T15:25:08.832327Z"},"trusted":true},"execution_count":3,"outputs":[]},{"cell_type":"code","source":"batch_size = 128\nlearning_rate = 1e-3  # Increased learning rate for better optimization\nnum_epochs = 100\nimg_size = 128","metadata":{"execution":{"iopub.status.busy":"2024-10-12T15:25:16.310596Z","iopub.execute_input":"2024-10-12T15:25:16.31161Z","iopub.status.idle":"2024-10-12T15:25:16.317403Z","shell.execute_reply.started":"2024-10-12T15:25:16.311549Z","shell.execute_reply":"2024-10-12T15:25:16.316048Z"},"trusted":true},"execution_count":4,"outputs":[]},{"cell_type":"code","source":"# Set seed\nimport os\nimport random\nimport numpy as np\nimport torch","metadata":{"execution":{"iopub.status.busy":"2024-10-12T15:25:29.476171Z","iopub.execute_input":"2024-10-12T15:25:29.476733Z","iopub.status.idle":"2024-10-12T15:25:29.482808Z","shell.execute_reply.started":"2024-10-12T15:25:29.476676Z","shell.execute_reply":"2024-10-12T15:25:29.481336Z"},"trusted":true},"execution_count":5,"outputs":[]},{"cell_type":"code","source":"random_seed = 42\nrandom.seed(random_seed)\nnp.random.seed(random_seed)\nos.environ[\"PYTHONHASHSEED\"] = str(random_seed)\ntorch.manual_seed(random_seed)\ntorch.cuda.manual_seed(random_seed)\ntorch.cuda.manual_seed_all(random_seed)\ntorch.backends.cudnn.deterministic = True\ntorch.backends.cudnn.benchmark = False\ntorch.use_deterministic_algorithms(False)","metadata":{"execution":{"iopub.status.busy":"2024-10-12T15:25:48.203285Z","iopub.execute_input":"2024-10-12T15:25:48.203712Z","iopub.status.idle":"2024-10-12T15:25:48.220889Z","shell.execute_reply.started":"2024-10-12T15:25:48.203671Z","shell.execute_reply":"2024-10-12T15:25:48.219418Z"},"trusted":true},"execution_count":6,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}