{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installedimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n\n!pip install ../input/modelsdefs/efficientnet_pytorch/ > /dev/null\npackage_path = '../input/rsnascripts'\nimport sys\nsys.path.append(package_path)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!ls ../input/rsna-intracranial-hemorrhage-detection/rsna-intracranial-hemorrhage-detection\n","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import torch\nimport torch.optim as optim\nfrom model import EfficientFPN\nfrom model import load_net\nfrom train import Trainer\n\n\nmodel = EfficientFPN(encoder_name='efficientnet-b4', classes=6, use_pretrained=0, \n                         grayscale=True, use_se_block=True, learn_window=True,\n                         use_stn = False) #TODO - evaluate losses\n\nstate = torch.load('../input/rsna-models/last.pth', map_location=lambda storage, loc: storage)\nload_net(state, model)\n#model.load_state_dict(state[\"state_dict\"])\ndevice = torch.device(\"cuda:0\")\nmodel = model.to(device)\noptimizer = optim.AdamW(model.parameters(), lr=1e-5, weight_decay=1e-5)\n\n\ntrain_df_path = '../input/rsna-intracranial-hemorrhage-detection/rsna-intracranial-hemorrhage-detection/stage_2_train.csv'\ndata_folder = \"../input/rsna-intracranial-hemorrhage-detection/rsna-intracranial-hemorrhage-detection/stage_2_train\"\n\nmodel_trainer = Trainer(model, batch_size = {\"train\": 16, \"val\": 8}, \n                        data_folder=data_folder, train_df_path=train_df_path, optimizer = optimizer, \n                        train_width=256, run_dir='.', base_lr=1e-5,\n                        num_epochs = 10, num_workers=8, \n                        from_epoch=0, finetune = False, load_pickle=False,\n                        balance = False, use_tqdm=False, tensorboard=False, use_ohem=True)\nmodel_trainer.start()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from IPython.display import FileLink\nFileLink(r'model.pth')\nFileLink(r'last.pth')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"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":4,"nbformat_minor":1}