Created
August 19, 2019 23:52
-
-
Save mmauri/303d4af9bf4b0a58cf7298d12af447af to your computer and use it in GitHub Desktop.
test_OversamplingCallback_Inference.ipynb
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| { | |
| "nbformat": 4, | |
| "nbformat_minor": 0, | |
| "metadata": { | |
| "kernelspec": { | |
| "name": "python3", | |
| "display_name": "Python 3" | |
| }, | |
| "language_info": { | |
| "codemirror_mode": { | |
| "name": "ipython", | |
| "version": 3 | |
| }, | |
| "file_extension": ".py", | |
| "mimetype": "text/x-python", | |
| "name": "python", | |
| "nbconvert_exporter": "python", | |
| "pygments_lexer": "ipython3", | |
| "version": "3.6.7" | |
| }, | |
| "colab": { | |
| "name": "test_OversamplingCallback_Inference.ipynb", | |
| "version": "0.3.2", | |
| "provenance": [], | |
| "collapsed_sections": [], | |
| "include_colab_link": true | |
| }, | |
| "accelerator": "GPU" | |
| }, | |
| "cells": [ | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "id": "view-in-github", | |
| "colab_type": "text" | |
| }, | |
| "source": [ | |
| "<a href=\"https://colab.research.google.com/gist/mmauri/303d4af9bf4b0a58cf7298d12af447af/test_oversamplingcallback_inference.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>" | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "bZ_YTqI8JhpE", | |
| "colab_type": "code", | |
| "colab": { | |
| "base_uri": "https://localhost:8080/", | |
| "height": 51 | |
| }, | |
| "outputId": "d7c4b6bf-6581-4f0d-a2dc-0cd1b82aea82" | |
| }, | |
| "source": [ | |
| "!curl -s https://course.fast.ai/setup/colab | bash" | |
| ], | |
| "execution_count": 1, | |
| "outputs": [ | |
| { | |
| "output_type": "stream", | |
| "text": [ | |
| "Updating fastai...\n", | |
| "Done.\n" | |
| ], | |
| "name": "stdout" | |
| } | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "hide_input": false, | |
| "id": "GXYvVpSZJFRY", | |
| "colab_type": "code", | |
| "colab": {} | |
| }, | |
| "source": [ | |
| "from fastai.vision import * # Quick access to computer vision functionality" | |
| ], | |
| "execution_count": 0, | |
| "outputs": [] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "tQZflfkXJFRd", | |
| "colab_type": "code", | |
| "colab": { | |
| "base_uri": "https://localhost:8080/", | |
| "height": 34 | |
| }, | |
| "outputId": "556a8d5a-2f32-426b-bcc9-3c326b406e6a" | |
| }, | |
| "source": [ | |
| "path = untar_data(URLs.MNIST_SAMPLE)\n", | |
| "path" | |
| ], | |
| "execution_count": 3, | |
| "outputs": [ | |
| { | |
| "output_type": "execute_result", | |
| "data": { | |
| "text/plain": [ | |
| "PosixPath('/root/.fastai/data/mnist_sample')" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| }, | |
| "execution_count": 3 | |
| } | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "LFMnTka5JFRj", | |
| "colab_type": "code", | |
| "colab": { | |
| "base_uri": "https://localhost:8080/", | |
| "height": 306 | |
| }, | |
| "outputId": "b4eedeb1-d015-4f19-ba2e-736f55793005" | |
| }, | |
| "source": [ | |
| "data = ImageDataBunch.from_folder(path, ds_tfms=(rand_pad(2, 28), []), bs=128)\n", | |
| "data.normalize(imagenet_stats)" | |
| ], | |
| "execution_count": 7, | |
| "outputs": [ | |
| { | |
| "output_type": "execute_result", | |
| "data": { | |
| "text/plain": [ | |
| "ImageDataBunch;\n", | |
| "\n", | |
| "Train: LabelList (12396 items)\n", | |
| "x: ImageList\n", | |
| "Image (3, 28, 28),Image (3, 28, 28),Image (3, 28, 28),Image (3, 28, 28),Image (3, 28, 28)\n", | |
| "y: CategoryList\n", | |
| "3,3,3,3,3\n", | |
| "Path: /root/.fastai/data/mnist_sample;\n", | |
| "\n", | |
| "Valid: LabelList (2038 items)\n", | |
| "x: ImageList\n", | |
| "Image (3, 28, 28),Image (3, 28, 28),Image (3, 28, 28),Image (3, 28, 28),Image (3, 28, 28)\n", | |
| "y: CategoryList\n", | |
| "3,3,3,3,3\n", | |
| "Path: /root/.fastai/data/mnist_sample;\n", | |
| "\n", | |
| "Test: None" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| }, | |
| "execution_count": 7 | |
| } | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "h3boB9GjJFRn", | |
| "colab_type": "code", | |
| "colab": {} | |
| }, | |
| "source": [ | |
| "from fastai.callbacks import *\n", | |
| "learn = cnn_learner(data, models.resnet18, \n", | |
| " metrics=accuracy,\n", | |
| " callback_fns=[OverSamplingCallback,ShowGraph]).to_fp16()\n" | |
| ], | |
| "execution_count": 0, | |
| "outputs": [] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "0RTQyirVJFRr", | |
| "colab_type": "code", | |
| "colab": { | |
| "base_uri": "https://localhost:8080/", | |
| "height": 332 | |
| }, | |
| "outputId": "98496fd3-61a2-40bb-f014-eaef3229baec" | |
| }, | |
| "source": [ | |
| "learn.fit_one_cycle(1)" | |
| ], | |
| "execution_count": 9, | |
| "outputs": [ | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "text/html": [ | |
| "<table border=\"1\" class=\"dataframe\">\n", | |
| " <thead>\n", | |
| " <tr style=\"text-align: left;\">\n", | |
| " <th>epoch</th>\n", | |
| " <th>train_loss</th>\n", | |
| " <th>valid_loss</th>\n", | |
| " <th>accuracy</th>\n", | |
| " <th>time</th>\n", | |
| " </tr>\n", | |
| " </thead>\n", | |
| " <tbody>\n", | |
| " <tr>\n", | |
| " <td>0</td>\n", | |
| " <td>0.269129</td>\n", | |
| " <td>0.157397</td>\n", | |
| " <td>0.944063</td>\n", | |
| " <td>00:08</td>\n", | |
| " </tr>\n", | |
| " </tbody>\n", | |
| "</table>" | |
| ], | |
| "text/plain": [ | |
| "<IPython.core.display.HTML object>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| }, | |
| { | |
| "output_type": "display_data", | |
| "data": { | |
| "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXcAAAD8CAYAAACMwORRAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nDQ/qBKcAAAAASUVORK5CYII=\n", | |
| "text/plain": [ | |
| "<Figure size 432x288 with 1 Axes>" | |
| ] | |
| }, | |
| "metadata": { | |
| "tags": [] | |
| } | |
| } | |
| ] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "HPx7I5FeJFRu", | |
| "colab_type": "code", | |
| "colab": {} | |
| }, | |
| "source": [ | |
| "learn.export(\"export.pkl\")" | |
| ], | |
| "execution_count": 0, | |
| "outputs": [] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "lrDaf1n0OTCn", | |
| "colab_type": "code", | |
| "colab": {} | |
| }, | |
| "source": [ | |
| "test_path=\"/content/data/mnist_sample/valid/3\"\n", | |
| "#test = ImageItemList.from_folder(test_path)\n", | |
| "test=ImageImageList.from_folder(test_path)\n" | |
| ], | |
| "execution_count": 0, | |
| "outputs": [] | |
| }, | |
| { | |
| "cell_type": "code", | |
| "metadata": { | |
| "id": "AjQokF-bQJYt", | |
| "colab_type": "code", | |
| "colab": { | |
| "base_uri": "https://localhost:8080/", | |
| "height": 323 | |
| }, | |
| "outputId": "0e20cc9c-bfa7-4c51-c414-d3001667cb41" | |
| }, | |
| "source": [ | |
| "learner = load_learner(path, file='export.pkl', test=test)\n", | |
| "preds, _ = learner.get_preds(ds_type=DatasetType.Test)" | |
| ], | |
| "execution_count": 32, | |
| "outputs": [ | |
| { | |
| "output_type": "error", | |
| "ename": "IndexError", | |
| "evalue": "ignored", | |
| "traceback": [ | |
| "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", | |
| "\u001b[0;31mIndexError\u001b[0m Traceback (most recent call last)", | |
| "\u001b[0;32m<ipython-input-32-201099be5822>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[0mlearner\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mload_learner\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mpath\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfile\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'export.pkl'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtest\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mtest\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0mpreds\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0m_\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mlearner\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_preds\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mds_type\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mDatasetType\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mTest\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m", | |
| "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/fastai/basic_train.py\u001b[0m in \u001b[0;36mget_preds\u001b[0;34m(self, ds_type, activ, with_loss, n_batch, pbar)\u001b[0m\n\u001b[1;32m 340\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mgetattr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'opt'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;32mFalse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcreate_opt\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlr\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mwd\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 341\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mopt\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlr\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mopt\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwd\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mlr\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mwd\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 342\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcallbacks\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0mcb\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mcb\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcallback_fns\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0mlistify\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdefaults\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mextra_callback_fns\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0mlistify\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcallbacks\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 343\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcb_fns_registered\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mTrue\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 344\u001b[0m return get_preds(self.model, self.dl(ds_type), cb_handler=CallbackHandler(self.callbacks),\n", | |
| "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/fastai/basic_train.py\u001b[0m in \u001b[0;36m<listcomp>\u001b[0;34m(.0)\u001b[0m\n\u001b[1;32m 340\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mgetattr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'opt'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;32mFalse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcreate_opt\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlr\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mwd\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 341\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mopt\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlr\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mopt\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwd\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mlr\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mwd\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 342\u001b[0;31m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcallbacks\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0mcb\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mcb\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcallback_fns\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0mlistify\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdefaults\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mextra_callback_fns\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0mlistify\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcallbacks\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 343\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcb_fns_registered\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mTrue\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 344\u001b[0m return get_preds(self.model, self.dl(ds_type), cb_handler=CallbackHandler(self.callbacks),\n", | |
| "\u001b[0;32m/usr/local/lib/python3.6/dist-packages/fastai/callbacks/oversampling.py\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, learn, weights)\u001b[0m\n\u001b[1;32m 15\u001b[0m \u001b[0m_\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcounts\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0munique\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlabels\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mreturn_counts\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 16\u001b[0m self.weights = (weights if weights is not None else\n\u001b[0;32m---> 17\u001b[0;31m torch.DoubleTensor((1/counts)[self.labels]))\n\u001b[0m\u001b[1;32m 18\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlabel_counts\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbincount\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlearn\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdata\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtrain_dl\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdataset\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0my\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mi\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdata\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mi\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mrange\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlearn\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdata\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtrain_dl\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdataset\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 19\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtotal_len_oversample\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlearn\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdata\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mc\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmax\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlabel_counts\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", | |
| "\u001b[0;31mIndexError\u001b[0m: arrays used as indices must be of integer (or boolean) type" | |
| ] | |
| } | |
| ] | |
| } | |
| ] | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment