summaryrefslogtreecommitdiff
path: root/notebooks/04-convnext.ipynb
diff options
context:
space:
mode:
Diffstat (limited to 'notebooks/04-convnext.ipynb')
-rw-r--r--notebooks/04-convnext.ipynb210
1 files changed, 210 insertions, 0 deletions
diff --git a/notebooks/04-convnext.ipynb b/notebooks/04-convnext.ipynb
new file mode 100644
index 0000000..6d70884
--- /dev/null
+++ b/notebooks/04-convnext.ipynb
@@ -0,0 +1,210 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 61,
+ "id": "7c02ae76-b540-4b16-9492-e9210b3b9249",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "The autoreload extension is already loaded. To reload it, use:\n",
+ " %reload_ext autoreload\n"
+ ]
+ }
+ ],
+ "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",
+ "\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": 62,
+ "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": 63,
+ "id": "3cf50475-39f2-4642-a7d1-5bcbc0a036f7",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "path = \"../training/conf/network/convnext.yaml\""
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 64,
+ "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": 65,
+ "id": "f939aa37-7b1d-45cc-885c-323c4540bda1",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "{'_target_': 'text_recognizer.networks.convnext.ConvNext', 'dim': 16, 'dim_mults': [2, 4, 8], 'depths': [3, 3, 6], 'downsampling_factors': [[2, 2], [2, 2], [2, 2]]}"
+ ]
+ },
+ "execution_count": 65,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "cfg"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 66,
+ "id": "aaeab329-aeb0-4a1b-aa35-5a2aab81b1d0",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "net = instantiate(cfg)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 67,
+ "id": "618b997c-e6a6-4487-b70c-9d260cb556d3",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "from torchinfo import summary"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 68,
+ "id": "25759b7b-8deb-4163-b75d-a1357c9fe88f",
+ "metadata": {
+ "scrolled": false
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "====================================================================================================\n",
+ "Layer (type:depth-idx) Output Shape Param #\n",
+ "====================================================================================================\n",
+ "ConvNext [2, 128, 7, 128] --\n",
+ "├─Conv2d: 1-1 [2, 16, 56, 1024] 800\n",
+ "├─ModuleList: 1-2 -- --\n",
+ "│ └─ModuleList: 2-1 -- --\n",
+ "│ │ └─ConvNextBlock: 3-1 [2, 16, 56, 1024] --\n",
+ "│ │ │ └─Conv2d: 4-1 [2, 16, 56, 1024] 800\n",
+ "│ │ │ └─Sequential: 4-2 [2, 16, 56, 1024] 9,280\n",
+ "│ │ │ └─Identity: 4-3 [2, 16, 56, 1024] --\n",
+ "│ │ └─ModuleList: 3-2 -- --\n",
+ "│ │ │ └─ConvNextBlock: 4-4 [2, 16, 56, 1024] 10,080\n",
+ "│ │ │ └─ConvNextBlock: 4-5 [2, 16, 56, 1024] 10,080\n",
+ "│ │ │ └─ConvNextBlock: 4-6 [2, 16, 56, 1024] 10,080\n",
+ "│ │ └─Downsample: 3-3 [2, 32, 28, 512] --\n",
+ "│ │ │ └─Sequential: 4-7 [2, 32, 28, 512] 2,080\n",
+ "│ └─ModuleList: 2-2 -- --\n",
+ "│ │ └─ConvNextBlock: 3-4 [2, 32, 28, 512] --\n",
+ "│ │ │ └─Conv2d: 4-8 [2, 32, 28, 512] 1,600\n",
+ "│ │ │ └─Sequential: 4-9 [2, 32, 28, 512] 36,992\n",
+ "│ │ │ └─Identity: 4-10 [2, 32, 28, 512] --\n",
+ "│ │ └─ModuleList: 3-5 -- --\n",
+ "│ │ │ └─ConvNextBlock: 4-11 [2, 32, 28, 512] 38,592\n",
+ "│ │ │ └─ConvNextBlock: 4-12 [2, 32, 28, 512] 38,592\n",
+ "│ │ │ └─ConvNextBlock: 4-13 [2, 32, 28, 512] 38,592\n",
+ "│ │ └─Downsample: 3-6 [2, 64, 14, 256] --\n",
+ "│ │ │ └─Sequential: 4-14 [2, 64, 14, 256] 8,256\n",
+ "│ └─ModuleList: 2-3 -- --\n",
+ "│ │ └─ConvNextBlock: 3-7 [2, 64, 14, 256] --\n",
+ "│ │ │ └─Conv2d: 4-15 [2, 64, 14, 256] 3,200\n",
+ "│ │ │ └─Sequential: 4-16 [2, 64, 14, 256] 147,712\n",
+ "│ │ │ └─Identity: 4-17 [2, 64, 14, 256] --\n",
+ "│ │ └─ModuleList: 3-8 -- --\n",
+ "│ │ │ └─ConvNextBlock: 4-18 [2, 64, 14, 256] 150,912\n",
+ "│ │ │ └─ConvNextBlock: 4-19 [2, 64, 14, 256] 150,912\n",
+ "│ │ │ └─ConvNextBlock: 4-20 [2, 64, 14, 256] 150,912\n",
+ "│ │ │ └─ConvNextBlock: 4-21 [2, 64, 14, 256] 150,912\n",
+ "│ │ │ └─ConvNextBlock: 4-22 [2, 64, 14, 256] 150,912\n",
+ "│ │ │ └─ConvNextBlock: 4-23 [2, 64, 14, 256] 150,912\n",
+ "│ │ └─Downsample: 3-9 [2, 128, 7, 128] --\n",
+ "│ │ │ └─Sequential: 4-24 [2, 128, 7, 128] 32,896\n",
+ "├─LayerNorm: 1-3 [2, 128, 7, 128] 128\n",
+ "====================================================================================================\n",
+ "Total params: 1,295,232\n",
+ "Trainable params: 1,295,232\n",
+ "Non-trainable params: 0\n",
+ "Total mult-adds (G): 16.88\n",
+ "====================================================================================================\n",
+ "Input size (MB): 0.46\n",
+ "Forward/backward pass size (MB): 598.21\n",
+ "Params size (MB): 5.18\n",
+ "Estimated Total Size (MB): 603.85\n",
+ "===================================================================================================="
+ ]
+ },
+ "execution_count": 68,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "summary(net, (2, 1, 56, 1024), device=\"cpu\", depth=4)"
+ ]
+ }
+ ],
+ "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
+}