diff options
Diffstat (limited to 'notebooks/04-efficientnet.ipynb')
| -rw-r--r-- | notebooks/04-efficientnet.ipynb | 279 |
1 files changed, 279 insertions, 0 deletions
diff --git a/notebooks/04-efficientnet.ipynb b/notebooks/04-efficientnet.ipynb new file mode 100644 index 0000000..4148e7d --- /dev/null +++ b/notebooks/04-efficientnet.ipynb @@ -0,0 +1,279 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 2, + "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", + "\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": 3, + "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": 4, + "id": "3cf50475-39f2-4642-a7d1-5bcbc0a036f7", + "metadata": {}, + "outputs": [], + "source": [ + "path = \"../training/conf/network/encoder/efficientnet.yaml\"" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "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": 6, + "id": "f939aa37-7b1d-45cc-885c-323c4540bda1", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "{'_target_': 'text_recognizer.networks.encoders.efficientnet.EfficientNet', 'arch': 'b0', 'out_channels': 1280, 'stochastic_dropout_rate': 0.2, 'bn_momentum': 0.99, 'bn_eps': 0.001}" + ] + }, + "execution_count": 6, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "cfg" + ] + }, + { + "cell_type": "code", + "execution_count": 7, + "id": "aaeab329-aeb0-4a1b-aa35-5a2aab81b1d0", + "metadata": {}, + "outputs": [], + "source": [ + "net = instantiate(cfg)" + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "id": "618b997c-e6a6-4487-b70c-9d260cb556d3", + "metadata": {}, + "outputs": [], + "source": [ + "from torchinfo import summary" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "id": "25759b7b-8deb-4163-b75d-a1357c9fe88f", + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "==========================================================================================\n", + "Layer (type:depth-idx) Output Shape Param #\n", + "==========================================================================================\n", + "EfficientNet -- --\n", + "├─ModuleList: 1-1 -- --\n", + "├─Sequential: 1-2 [2, 32, 288, 320] --\n", + "│ └─ZeroPad2d: 2-1 [2, 1, 577, 641] --\n", + "│ └─Conv2d: 2-2 [2, 32, 288, 320] 288\n", + "│ └─BatchNorm2d: 2-3 [2, 32, 288, 320] 64\n", + "│ └─Mish: 2-4 [2, 32, 288, 320] --\n", + "├─ModuleList: 1-1 -- --\n", + "│ └─MBConvBlock: 2-5 [2, 16, 288, 320] --\n", + "│ │ └─Sequential: 3-1 [2, 32, 288, 320] 352\n", + "│ │ └─Sequential: 3-2 [2, 32, 288, 320] 552\n", + "│ │ └─Sequential: 3-3 [2, 16, 288, 320] 544\n", + "│ └─MBConvBlock: 2-6 [2, 24, 144, 160] --\n", + "│ │ └─Sequential: 3-4 [2, 96, 288, 320] 1,728\n", + "│ │ └─Sequential: 3-5 [2, 96, 144, 160] 1,056\n", + "│ │ └─Sequential: 3-6 [2, 96, 144, 160] 4,728\n", + "│ │ └─Sequential: 3-7 [2, 24, 144, 160] 2,352\n", + "│ └─MBConvBlock: 2-7 [2, 24, 144, 160] --\n", + "│ │ └─Sequential: 3-8 [2, 144, 144, 160] 3,744\n", + "│ │ └─Sequential: 3-9 [2, 144, 144, 160] 1,584\n", + "│ │ └─Sequential: 3-10 [2, 144, 144, 160] 10,548\n", + "│ │ └─Sequential: 3-11 [2, 24, 144, 160] 3,504\n", + "│ └─MBConvBlock: 2-8 [2, 40, 72, 80] --\n", + "│ │ └─Sequential: 3-12 [2, 144, 144, 160] 3,744\n", + "│ │ └─Sequential: 3-13 [2, 144, 72, 80] 3,888\n", + "│ │ └─Sequential: 3-14 [2, 144, 72, 80] 10,548\n", + "│ │ └─Sequential: 3-15 [2, 40, 72, 80] 5,840\n", + "│ └─MBConvBlock: 2-9 [2, 40, 72, 80] --\n", + "│ │ └─Sequential: 3-16 [2, 240, 72, 80] 10,080\n", + "│ │ └─Sequential: 3-17 [2, 240, 72, 80] 6,480\n", + "│ │ └─Sequential: 3-18 [2, 240, 72, 80] 29,100\n", + "│ │ └─Sequential: 3-19 [2, 40, 72, 80] 9,680\n", + "│ └─MBConvBlock: 2-10 [2, 80, 36, 40] --\n", + "│ │ └─Sequential: 3-20 [2, 240, 72, 80] 10,080\n", + "│ │ └─Sequential: 3-21 [2, 240, 36, 40] 2,640\n", + "│ │ └─Sequential: 3-22 [2, 240, 36, 40] 29,100\n", + "│ │ └─Sequential: 3-23 [2, 80, 36, 40] 19,360\n", + "│ └─MBConvBlock: 2-11 [2, 80, 36, 40] --\n", + "│ │ └─Sequential: 3-24 [2, 480, 36, 40] 39,360\n", + "│ │ └─Sequential: 3-25 [2, 480, 36, 40] 5,280\n", + "│ │ └─Sequential: 3-26 [2, 480, 36, 40] 115,800\n", + "│ │ └─Sequential: 3-27 [2, 80, 36, 40] 38,560\n", + "│ └─MBConvBlock: 2-12 [2, 80, 36, 40] --\n", + "│ │ └─Sequential: 3-28 [2, 480, 36, 40] 39,360\n", + "│ │ └─Sequential: 3-29 [2, 480, 36, 40] 5,280\n", + "│ │ └─Sequential: 3-30 [2, 480, 36, 40] 115,800\n", + "│ │ └─Sequential: 3-31 [2, 80, 36, 40] 38,560\n", + "│ └─MBConvBlock: 2-13 [2, 112, 36, 40] --\n", + "│ │ └─Sequential: 3-32 [2, 480, 36, 40] 39,360\n", + "│ │ └─Sequential: 3-33 [2, 480, 36, 40] 12,960\n", + "│ │ └─Sequential: 3-34 [2, 480, 36, 40] 115,800\n", + "│ │ └─Sequential: 3-35 [2, 112, 36, 40] 53,984\n", + "│ └─MBConvBlock: 2-14 [2, 112, 36, 40] --\n", + "│ │ └─Sequential: 3-36 [2, 672, 36, 40] 76,608\n", + "│ │ └─Sequential: 3-37 [2, 672, 36, 40] 18,144\n", + "│ │ └─Sequential: 3-38 [2, 672, 36, 40] 226,632\n", + "│ │ └─Sequential: 3-39 [2, 112, 36, 40] 75,488\n", + "│ └─MBConvBlock: 2-15 [2, 112, 36, 40] --\n", + "│ │ └─Sequential: 3-40 [2, 672, 36, 40] 76,608\n", + "│ │ └─Sequential: 3-41 [2, 672, 36, 40] 18,144\n", + "│ │ └─Sequential: 3-42 [2, 672, 36, 40] 226,632\n", + "│ │ └─Sequential: 3-43 [2, 112, 36, 40] 75,488\n", + "│ └─MBConvBlock: 2-16 [2, 192, 18, 20] --\n", + "│ │ └─Sequential: 3-44 [2, 672, 36, 40] 76,608\n", + "│ │ └─Sequential: 3-45 [2, 672, 18, 20] 18,144\n", + "│ │ └─Sequential: 3-46 [2, 672, 18, 20] 226,632\n", + "│ │ └─Sequential: 3-47 [2, 192, 18, 20] 129,408\n", + "│ └─MBConvBlock: 2-17 [2, 192, 18, 20] --\n", + "│ │ └─Sequential: 3-48 [2, 1152, 18, 20] 223,488\n", + "│ │ └─Sequential: 3-49 [2, 1152, 18, 20] 31,104\n", + "│ │ └─Sequential: 3-50 [2, 1152, 18, 20] 664,992\n", + "│ │ └─Sequential: 3-51 [2, 192, 18, 20] 221,568\n", + "│ └─MBConvBlock: 2-18 [2, 192, 18, 20] --\n", + "│ │ └─Sequential: 3-52 [2, 1152, 18, 20] 223,488\n", + "│ │ └─Sequential: 3-53 [2, 1152, 18, 20] 31,104\n", + "│ │ └─Sequential: 3-54 [2, 1152, 18, 20] 664,992\n", + "│ │ └─Sequential: 3-55 [2, 192, 18, 20] 221,568\n", + "│ └─MBConvBlock: 2-19 [2, 192, 18, 20] --\n", + "│ │ └─Sequential: 3-56 [2, 1152, 18, 20] 223,488\n", + "│ │ └─Sequential: 3-57 [2, 1152, 18, 20] 31,104\n", + "│ │ └─Sequential: 3-58 [2, 1152, 18, 20] 664,992\n", + "│ │ └─Sequential: 3-59 [2, 192, 18, 20] 221,568\n", + "│ └─MBConvBlock: 2-20 [2, 320, 18, 20] --\n", + "│ │ └─Sequential: 3-60 [2, 1152, 18, 20] 223,488\n", + "│ │ └─Sequential: 3-61 [2, 1152, 18, 20] 12,672\n", + "│ │ └─Sequential: 3-62 [2, 1152, 18, 20] 664,992\n", + "│ │ └─Sequential: 3-63 [2, 320, 18, 20] 369,280\n", + "├─Sequential: 1-3 [2, 1280, 18, 20] --\n", + "│ └─Conv2d: 2-21 [2, 1280, 18, 20] 409,600\n", + "│ └─BatchNorm2d: 2-22 [2, 1280, 18, 20] 2,560\n", + "==========================================================================================\n", + "Total params: 7,142,272\n", + "Trainable params: 7,142,272\n", + "Non-trainable params: 0\n", + "Total mult-adds (G): 11.27\n", + "==========================================================================================\n", + "Input size (MB): 2.95\n", + "Forward/backward pass size (MB): 1922.96\n", + "Params size (MB): 28.57\n", + "Estimated Total Size (MB): 1954.48\n", + "==========================================================================================" + ] + }, + "execution_count": 9, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "summary(net, (2, 1, 576, 640), device=\"cpu\")" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "id": "3ef95a63-7044-45bf-a085-faf5ea0c03ec", + "metadata": {}, + "outputs": [ + { + "ename": "TypeError", + "evalue": "'EfficientNet' object is not subscriptable", + "output_type": "error", + "traceback": [ + "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[0;31mTypeError\u001b[0m Traceback (most recent call last)", + "\u001b[0;32m/tmp/ipykernel_2800/4064962505.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mnet\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m-\u001b[0m\u001b[0;36m2\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m", + "\u001b[0;31mTypeError\u001b[0m: 'EfficientNet' object is not subscriptable" + ] + } + ], + "source": [ + "net[:-2]" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "62ca0d97-625c-474b-8d6c-d0caba79e198", + "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": "3.9.7" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} |