{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"%reload_ext autoreload\n%autoreload 2\n%matplotlib inline","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"from fastai import *\nfrom fastai.vision import *\nimport numpy as np # linear algebra\nimport pandas as pd ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import os\npath = '../input'\nprint(os.listdir(path))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\nclass CustomImageList(ImageList):\n    def open(self, fn):\n        img = fn.reshape(28,28)\n        img = np.stack((img,)*3, axis=-1)\n        return Image(pil2tensor(img, dtype=np.float32))\n    \n    @classmethod\n    def from_csv_custom(cls, path:PathOrStr, csv_name:str, imgIdx:int=1, header:str='infer', **kwargs)->'ItemList': \n        df = pd.read_csv(Path(path)/csv_name, header=header)\n        res = super().from_df(df, path=path, cols=0, **kwargs)\n        \n        res.items = df.iloc[:,imgIdx:].apply(lambda x: x.values / 255.0, axis=1).values\n        \n        return res\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test = CustomImageList.from_csv_custom(path=path, csv_name='test.csv', imgIdx=0)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"    tfms = get_transforms(do_flip=False)\n    data = (CustomImageList.from_csv_custom(path=path, csv_name='train.csv', imgIdx=1)\n                .split_by_rand_pct(.2)\n                .label_from_df(cols='label')\n                .add_test(test, label=0)\n                 #src.transform(tfms, size=256)\n                .transform(tfms,size=28)\n                .databunch(bs=128, num_workers=0)\n                .normalize(imagenet_stats))\n    data.show_batch(rows=3, figsize=(5,5))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#learn = cnn_learner(data, models.resnet34, metrics=accuracy, model_dir='/kaggle/working/models')\nlearn = cnn_learner(data, models.resnet50, metrics=accuracy, model_dir='/kaggle/working/models')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data.show_batch(rows=3, figsize=(5,5))\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.fit_one_cycle(4)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Training with different sizes"},{"metadata":{"trusted":true},"cell_type":"code","source":"classes = [10,14,18,22,25,28]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"for c in classes:\n    tfms = get_transforms(do_flip=False)\n    data = (CustomImageList.from_csv_custom(path=path, csv_name='train.csv', imgIdx=1)\n                .split_by_rand_pct(.2)\n                .label_from_df(cols='label')\n                .add_test(test, label=0)\n                 #src.transform(tfms, size=256)\n                .transform(tfms,size=c)\n                .databunch(bs=128, num_workers=0)\n                .normalize(imagenet_stats))\n    data.show_batch(rows=3, figsize=(5,5))\n    learn.data = data\n    c\n    learn.fit_one_cycle(8)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#learn.data = data","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.save('stage-1-resnet50')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.load('stage-1-resnet50')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.lr_find()\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.recorder.plot()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.unfreeze()\nlearn.fit_one_cycle(12, max_lr=slice(1e-6,5e-2))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.save('stage-1-resnet50')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.load('stage-1-resnet50')\nlearn.validate()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.unfreeze()\nlearn.lr_find()\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.recorder.plot()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.unfreeze()\nlearn.fit_one_cycle(4, max_lr=slice(1e-6,1e-4))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.save('stage-1-resnet50')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.load('stage-1-resnet50')\nlearn.validate()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#learn.lr_find()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#learn.recorder.plot()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#learn.lr_find()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#learn.recorder.plot()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#learn.unfreeze()\n#learn.fit_one_cycle(5,1e-4)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#learn.save('stage-1-resnet50')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#learn.load('stage-1-resnet50')\n#learn.validate()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#learn.lr_find()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#learn.recorder.plot()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#learn.unfreeze()\n#learn.fit_one_cycle(8, max_lr=slice(1e-5, 2.5e-4))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#learn.save('stage-1-resnet50')\n#learn.load('stage-1-resnet50')\n#learn.validate()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# get the predictions\npredictions, *_ = learn.get_preds(DatasetType.Test)\nlabels = np.argmax(predictions, 1)\n# output to a file\nsubmission_df = pd.DataFrame({'ImageId': list(range(1,len(labels)+1)), 'Label': labels})\nsubmission_df.to_csv(f'submission.csv', index=False)","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.4","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}