Rename mapping to tokenizer

1 files changed, 20 insertions, 13 deletions

diff --git a/notebooks/01-look-at-emnist.ipynb b/notebooks/01-look-at-emnist.ipynb
index a8b361b..8c5d54e 100644
--- a/notebooks/01-look-at-emnist.ipynb
+++ b/notebooks/01-look-at-emnist.ipynb
@@ -4,7 +4,16 @@
    "cell_type": "code",
    "execution_count": 1,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/aktersnurra/.cache/pypoetry/virtualenvs/text-recognizer-ejNaVa9M-py3.9/lib/python3.9/site-packages/torchvision/io/image.py:13: UserWarning: Failed to load image Python extension: /home/aktersnurra/.cache/pypoetry/virtualenvs/text-recognizer-ejNaVa9M-py3.9/lib/python3.9/site-packages/torchvision/image.so: undefined symbol: _ZNK3c1010TensorImpl36is_contiguous_nondefault_policy_implENS_12MemoryFormatE\n",
+      "  warn(f\"Failed to load image Python extension: {e}\")\n"
+     ]
+    }
+   ],
    "source": [
     "%load_ext autoreload\n",
     "%autoreload 2\n",
@@ -27,17 +36,15 @@
    "metadata": {},
    "outputs": [
     {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "EMNIST Dataset\n",
-      "Num classes: 83\n",
-      "Mapping: ['<b>', '<s>', '</s>', '<p>', '0', '1', '2', '3', '4', '5', '6', '7', '8', '9', 'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M', 'N', 'O', 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z', 'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 'q', 'r', 's', 't', 'u', 'v', 'w', 'x', 'y', 'z', ' ', '!', '\"', '#', '&', \"'\", '(', ')', '*', '+', ',', '-', '.', '/', ':', ';', '?']\n",
-      "Dims: (1, 28, 28)\n",
-      "Train/val/test sizes: 260276, 65070, 54028\n",
-      "Batch x stats: (torch.Size([128, 1, 28, 28]), torch.float32, tensor(0.), tensor(0.1673), tensor(0.3277), tensor(1.))\n",
-      "Batch y stats: (torch.Size([128]), torch.int64, tensor(4), tensor(65))\n",
-      "\n"
+     "ename": "TypeError",
+     "evalue": "__init__() missing 1 required positional argument: 'tokenizer'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn [2], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m data \u001b[38;5;241m=\u001b[39m EMNIST()\n\u001b[1;32m      2\u001b[0m data\u001b[38;5;241m.\u001b[39mprepare_data()\n\u001b[1;32m      3\u001b[0m data\u001b[38;5;241m.\u001b[39msetup()\n",
+      "File \u001b[0;32m~/projects/text-recognizer/text_recognizer/data/emnist.py:33\u001b[0m, in \u001b[0;36mEMNIST.__init__\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m     32\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m__init__\u001b[39m(\u001b[38;5;28mself\u001b[39m) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m---> 33\u001b[0m     \u001b[38;5;28;43msuper\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[38;5;21;43m__init__\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     34\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdims \u001b[38;5;241m=\u001b[39m (\u001b[38;5;241m1\u001b[39m, \u001b[38;5;241m*\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtokenizer\u001b[38;5;241m.\u001b[39minput_size)\n",
+      "\u001b[0;31mTypeError\u001b[0m: __init__() missing 1 required positional argument: 'tokenizer'"
      ]
     }
    ],
@@ -120,7 +127,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.7"
+   "version": "3.9.4"
   }
  },
  "nbformat": 4,