Working Emnist lines dataset.

1 files changed, 148 insertions, 0 deletions

diff --git a/src/notebooks/01b-dataset_normalization.ipynb b/src/notebooks/01b-dataset_normalization.ipynb
new file mode 100644
index 0000000..9421816
--- /dev/null
+++ b/src/notebooks/01b-dataset_normalization.ipynb
@@ -0,0 +1,148 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%load_ext autoreload\n",
+    "%autoreload 2\n",
+    "\n",
+    "%matplotlib inline\n",
+    "import matplotlib.pyplot as plt\n",
+    "import numpy as np\n",
+    "from PIL import Image\n",
+    "import torch\n",
+    "from importlib.util import find_spec\n",
+    "if find_spec(\"text_recognizer\") is None:\n",
+    "    import sys\n",
+    "    sys.path.append('..')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from text_recognizer.datasets import EmnistDataLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data_loaders = EmnistDataLoader(splits=[\"train\"], sample_to_balance=True,\n",
+    "        subsample_fraction = None,\n",
+    "        transform = None,\n",
+    "        target_transform = None,\n",
+    "        batch_size = 512,\n",
+    "        shuffle = True,\n",
+    "        num_workers  = 0,\n",
+    "        cuda = False,\n",
+    "        seed = 4711)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = data_loaders(\"train\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "mean = 0.\n",
+    "std = 0.\n",
+    "nb_samples = 0.\n",
+    "for data in loader:\n",
+    "    data, _ = data\n",
+    "    batch_samples = data.size(0)\n",
+    "    data = data.view(batch_samples, data.size(1), -1)\n",
+    "    mean += data.mean(2).sum(0)\n",
+    "    std += data.std(2).sum(0)\n",
+    "    nb_samples += batch_samples\n",
+    "\n",
+    "mean /= nb_samples\n",
+    "std /= nb_samples"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "tensor([0.1731])"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "mean"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "tensor([0.3247])"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "std"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}