diff options
Diffstat (limited to 'notebooks/Untitled1.ipynb')
| -rw-r--r-- | notebooks/Untitled1.ipynb | 111 |
1 files changed, 109 insertions, 2 deletions
diff --git a/notebooks/Untitled1.ipynb b/notebooks/Untitled1.ipynb index 92b35c9..d996e98 100644 --- a/notebooks/Untitled1.ipynb +++ b/notebooks/Untitled1.ipynb @@ -2,12 +2,24 @@ "cells": [ { "cell_type": "code", - "execution_count": 73, + "execution_count": 14, "id": "a15a452c-bbbc-4227-90fb-ad573f82c43f", "metadata": { "tags": [] }, - "outputs": [], + "outputs": [ + { + "ename": "ModuleNotFoundError", + "evalue": "No module named 'text_recognizer.network.transformer.embeddings'", + "output_type": "error", + "traceback": [ + "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[0;31mModuleNotFoundError\u001b[0m Traceback (most recent call last)", + "Cell \u001b[0;32mIn[14], line 15\u001b[0m\n\u001b[1;32m 12\u001b[0m sys\u001b[38;5;241m.\u001b[39mpath\u001b[38;5;241m.\u001b[39mappend(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m..\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[1;32m 14\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtext_recognizer\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mdata\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01miam_lines\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m IAMLines\n\u001b[0;32m---> 15\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtext_recognizer\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mnetwork\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mtransformer\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01membeddings\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01msincos\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m sincos_2d\n", + "\u001b[0;31mModuleNotFoundError\u001b[0m: No module named 'text_recognizer.network.transformer.embeddings'" + ] + } + ], "source": [ "import matplotlib.pyplot as plt\n", "import numpy as np\n", @@ -430,6 +442,101 @@ "plt.figure(figsize=(40, 20))\n", "plt.imshow(xxx, cmap='gray')" ] + }, + { + "cell_type": "code", + "execution_count": 18, + "id": "4535cb1c-fc97-4393-8348-649d06030931", + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "conv = torch.nn.Conv2d(1, 1, kernel_size=3, stride=2)" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "id": "d3092482-a2d5-4b52-9967-8d18cab35f42", + "metadata": { + "tags": [] + }, + "outputs": [ + { + "data": { + "text/plain": [ + "torch.Size([1, 1, 13, 255])" + ] + }, + "execution_count": 19, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "x = torch.randn(1, 1, 56, 1024)\n", + "conv(conv(x)).shape" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "id": "44183fe9-f798-4755-8db5-491b8a3dbf2f", + "metadata": { + "tags": [] + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "tensor([[True, True, True],\n", + " [True, True, True]])\n" + ] + } + ], + "source": [ + "import torch\n", + "import torch.nn.functional as F\n", + "source = torch.randn((2,3)).bool()\n", + "print(source)\n", + "# now we expand to size (7, 11) by appending a row of 0s at pos 0 and pos 6, \n", + "# and a column of 0s at pos 10\n", + "result = F.pad(source, pad=(0, 1), value=False)" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "id": "34220755-4224-458e-94b8-ea1fa0488a65", + "metadata": { + "tags": [] + }, + "outputs": [ + { + "data": { + "text/plain": [ + "tensor([[ True, True, True, False],\n", + " [ True, True, True, False]])" + ] + }, + "execution_count": 19, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "result" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "dfc269b8-8242-41ee-9190-73df0af47e83", + "metadata": {}, + "outputs": [], + "source": [] } ], "metadata": { |