summaryrefslogtreecommitdiff
path: root/notebooks/04-vit-lines.ipynb
diff options
context:
space:
mode:
authorGustaf Rydholm <gustaf.rydholm@gmail.com>2023-09-11 22:09:53 +0200
committerGustaf Rydholm <gustaf.rydholm@gmail.com>2023-09-11 22:09:53 +0200
commit43b10ea57f40983ec53c17a05f5b9fd2501f4eea (patch)
tree756b4cd2483a0d794b057cb6bb398f99991b01e1 /notebooks/04-vit-lines.ipynb
parent1732ed564a738a42c1bf6e8127ae810f5658cb06 (diff)
Update notebooks
Diffstat (limited to 'notebooks/04-vit-lines.ipynb')
-rw-r--r--notebooks/04-vit-lines.ipynb305
1 files changed, 0 insertions, 305 deletions
diff --git a/notebooks/04-vit-lines.ipynb b/notebooks/04-vit-lines.ipynb
deleted file mode 100644
index b87f38c..0000000
--- a/notebooks/04-vit-lines.ipynb
+++ /dev/null
@@ -1,305 +0,0 @@
-{
- "cells": [
- {
- "cell_type": "code",
- "execution_count": 1,
- "id": "7c02ae76-b540-4b16-9492-e9210b3b9249",
- "metadata": {},
- "outputs": [],
- "source": [
- "import os\n",
- "os.environ['CUDA_VISIBLE_DEVICE'] = ''\n",
- "import random\n",
- "\n",
- "%matplotlib inline\n",
- "import matplotlib.pyplot as plt\n",
- "\n",
- "import numpy as np\n",
- "from omegaconf import OmegaConf\n",
- "import torch\n",
- "%load_ext autoreload\n",
- "%autoreload 2\n",
- "\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,
- "id": "ccdb6dde-47e5-429a-88f2-0764fb7e259a",
- "metadata": {},
- "outputs": [],
- "source": [
- "from hydra import compose, initialize\n",
- "from omegaconf import OmegaConf\n",
- "from hydra.utils import instantiate"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 3,
- "id": "3cf50475-39f2-4642-a7d1-5bcbc0a036f7",
- "metadata": {},
- "outputs": [],
- "source": [
- "path = \"../training/conf/network/vit_lines.yaml\""
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 38,
- "id": "e52ecb01-c975-4e55-925d-1182c7aea473",
- "metadata": {},
- "outputs": [],
- "source": [
- "with open(path, \"rb\") as f:\n",
- " cfg = OmegaConf.load(f)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 39,
- "id": "f939aa37-7b1d-45cc-885c-323c4540bda1",
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "{'_target_': 'text_recognizer.network.vit.VisionTransformer', 'image_height': 56, 'image_width': 1024, 'patch_height': 28, 'patch_width': 32, 'dim': 256, 'num_classes': 57, 'encoder': {'_target_': 'text_recognizer.network.transformer.encoder.Encoder', 'dim': 256, 'inner_dim': 1024, 'heads': 8, 'dim_head': 64, 'depth': 6, 'dropout_rate': 0.0}, 'decoder': {'_target_': 'text_recognizer.network.transformer.decoder.Decoder', 'dim': 256, 'inner_dim': 1024, 'heads': 8, 'dim_head': 64, 'depth': 6, 'dropout_rate': 0.0}, 'token_embedding': {'_target_': 'text_recognizer.network.transformer.embedding.token.TokenEmbedding', 'num_tokens': 57, 'dim': 256, 'use_l2': True}, 'pos_embedding': {'_target_': 'text_recognizer.network.transformer.embedding.absolute.AbsolutePositionalEmbedding', 'dim': 256, 'max_length': 89, 'use_l2': True}, 'tie_embeddings': True, 'pad_index': 3}"
- ]
- },
- "execution_count": 39,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "cfg"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 40,
- "id": "aaeab329-aeb0-4a1b-aa35-5a2aab81b1d0",
- "metadata": {},
- "outputs": [],
- "source": [
- "net = instantiate(cfg)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 41,
- "id": "618b997c-e6a6-4487-b70c-9d260cb556d3",
- "metadata": {},
- "outputs": [],
- "source": [
- "from torchinfo import summary"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 43,
- "id": "7daf1f49",
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "====================================================================================================\n",
- "Layer (type:depth-idx) Output Shape Param #\n",
- "====================================================================================================\n",
- "VisionTransformer [1, 57, 89] --\n",
- "├─Sequential: 1-1 [1, 64, 256] --\n",
- "│ └─Rearrange: 2-1 [1, 64, 896] --\n",
- "│ └─LayerNorm: 2-2 [1, 64, 896] 1,792\n",
- "│ └─Linear: 2-3 [1, 64, 256] 229,632\n",
- "│ └─LayerNorm: 2-4 [1, 64, 256] 512\n",
- "├─Encoder: 1-2 [1, 64, 256] --\n",
- "│ └─ModuleList: 2-5 -- --\n",
- "│ │ └─ModuleList: 3-1 -- --\n",
- "│ │ │ └─Attention: 4-1 [1, 64, 256] 525,824\n",
- "│ │ │ └─FeedForward: 4-2 [1, 64, 256] 526,080\n",
- "│ │ └─ModuleList: 3-2 -- --\n",
- "│ │ │ └─Attention: 4-3 [1, 64, 256] 525,824\n",
- "│ │ │ └─FeedForward: 4-4 [1, 64, 256] 526,080\n",
- "│ │ └─ModuleList: 3-3 -- --\n",
- "│ │ │ └─Attention: 4-5 [1, 64, 256] 525,824\n",
- "│ │ │ └─FeedForward: 4-6 [1, 64, 256] 526,080\n",
- "│ │ └─ModuleList: 3-4 -- --\n",
- "│ │ │ └─Attention: 4-7 [1, 64, 256] 525,824\n",
- "│ │ │ └─FeedForward: 4-8 [1, 64, 256] 526,080\n",
- "│ │ └─ModuleList: 3-5 -- --\n",
- "│ │ │ └─Attention: 4-9 [1, 64, 256] 525,824\n",
- "│ │ │ └─FeedForward: 4-10 [1, 64, 256] 526,080\n",
- "│ │ └─ModuleList: 3-6 -- --\n",
- "│ │ │ └─Attention: 4-11 [1, 64, 256] 525,824\n",
- "│ │ │ └─FeedForward: 4-12 [1, 64, 256] 526,080\n",
- "│ └─LayerNorm: 2-6 [1, 64, 256] 512\n",
- "├─TokenEmbedding: 1-3 [1, 89, 256] --\n",
- "│ └─Embedding: 2-7 [1, 89, 256] 14,592\n",
- "├─AbsolutePositionalEmbedding: 1-4 [89, 256] --\n",
- "│ └─Embedding: 2-8 [89, 256] 22,784\n",
- "├─Decoder: 1-5 [1, 89, 256] --\n",
- "│ └─ModuleList: 2-9 -- --\n",
- "│ │ └─ModuleList: 3-7 -- --\n",
- "│ │ │ └─Attention: 4-13 [1, 89, 256] 525,824\n",
- "│ │ │ └─FeedForward: 4-14 [1, 89, 256] 526,080\n",
- "│ │ │ └─Attention: 4-15 [1, 89, 256] 525,824\n",
- "│ │ └─ModuleList: 3-8 -- --\n",
- "│ │ │ └─Attention: 4-16 [1, 89, 256] 525,824\n",
- "│ │ │ └─FeedForward: 4-17 [1, 89, 256] 526,080\n",
- "│ │ │ └─Attention: 4-18 [1, 89, 256] 525,824\n",
- "│ │ └─ModuleList: 3-9 -- --\n",
- "│ │ │ └─Attention: 4-19 [1, 89, 256] 525,824\n",
- "│ │ │ └─FeedForward: 4-20 [1, 89, 256] 526,080\n",
- "│ │ │ └─Attention: 4-21 [1, 89, 256] 525,824\n",
- "│ │ └─ModuleList: 3-10 -- --\n",
- "│ │ │ └─Attention: 4-22 [1, 89, 256] 525,824\n",
- "│ │ │ └─FeedForward: 4-23 [1, 89, 256] 526,080\n",
- "│ │ │ └─Attention: 4-24 [1, 89, 256] 525,824\n",
- "│ │ └─ModuleList: 3-11 -- --\n",
- "│ │ │ └─Attention: 4-25 [1, 89, 256] 525,824\n",
- "│ │ │ └─FeedForward: 4-26 [1, 89, 256] 526,080\n",
- "│ │ │ └─Attention: 4-27 [1, 89, 256] 525,824\n",
- "│ │ └─ModuleList: 3-12 -- --\n",
- "│ │ │ └─Attention: 4-28 [1, 89, 256] 525,824\n",
- "│ │ │ └─FeedForward: 4-29 [1, 89, 256] 526,080\n",
- "│ │ │ └─Attention: 4-30 [1, 89, 256] 525,824\n",
- "│ └─LayerNorm: 2-10 [1, 89, 256] 512\n",
- "====================================================================================================\n",
- "Total params: 16,048,128\n",
- "Trainable params: 16,048,128\n",
- "Non-trainable params: 0\n",
- "Total mult-adds (M): 18.03\n",
- "====================================================================================================\n",
- "Input size (MB): 0.23\n",
- "Forward/backward pass size (MB): 46.52\n",
- "Params size (MB): 64.16\n",
- "Estimated Total Size (MB): 110.91\n",
- "===================================================================================================="
- ]
- },
- "execution_count": 43,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "summary(net, ((1, 1, 56, 1024), (1, 89)), device=\"cpu\", depth=4)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 20,
- "id": "1b1a8ac0-bd05-4076-90c2-2de6b740490d",
- "metadata": {
- "tags": []
- },
- "outputs": [],
- "source": [
- "import torch"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 24,
- "id": "248a0cb1",
- "metadata": {},
- "outputs": [],
- "source": [
- "t = net(torch.randn(1, 1, 56, 1024), torch.randint(1, 4, (1, 4)))"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 25,
- "id": "c251a954-00ac-4680-87e4-f27b6ce06023",
- "metadata": {
- "tags": []
- },
- "outputs": [
- {
- "data": {
- "text/plain": [
- "torch.Size([1, 58, 4])"
- ]
- },
- "execution_count": 25,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "t.shape"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 17,
- "id": "02d82c5e-4e67-4f87-a539-393e4cf59b6e",
- "metadata": {
- "tags": []
- },
- "outputs": [],
- "source": [
- "loss = torch.nn.CrossEntropyLoss()"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 19,
- "id": "dc836993-a5d8-43b2-b41c-158a17990075",
- "metadata": {
- "tags": []
- },
- "outputs": [
- {
- "data": {
- "text/plain": [
- "tensor(4.0604, grad_fn=<NllLoss2DBackward0>)"
- ]
- },
- "execution_count": 19,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "loss(t.permute(0, 2, 1), torch.randint(0, 58, (1, 89)))"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "166bf656-aba6-4654-a530-dfce12666297",
- "metadata": {},
- "outputs": [],
- "source": []
- }
- ],
- "metadata": {
- "kernelspec": {
- "display_name": "Python 3 (ipykernel)",
- "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": "3.9.4"
- }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}