Efficientnet working

1 files changed, 172 insertions, 26 deletions

diff --git a/notebooks/00-scratch-pad.ipynb b/notebooks/00-scratch-pad.ipynb
index 1816021..32f96d1 100644
--- a/notebooks/00-scratch-pad.ipynb
+++ b/notebooks/00-scratch-pad.ipynb
@@ -2,18 +2,9 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 1,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "The autoreload extension is already loaded. To reload it, use:\n",
-      "  %reload_ext autoreload\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "%load_ext autoreload\n",
     "%autoreload 2\n",
@@ -39,13 +30,180 @@
   },
   {
    "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from text_recognizer.networks.encoders.efficientnet.efficientnet import EfficientNet"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 63,
+   "metadata": {
+    "scrolled": false
+   },
+   "outputs": [],
+   "source": [
+    "en = EfficientNet(\"b0\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 64,
+   "metadata": {
+    "scrolled": false
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "==========================================================================================\n",
+      "Layer (type:depth-idx)                   Output Shape              Param #\n",
+      "==========================================================================================\n",
+      "├─Sequential: 1-1                        [-1, 32, 111, 111]        --\n",
+      "|    └─Conv2d: 2-1                       [-1, 32, 111, 111]        288\n",
+      "|    └─BatchNorm2d: 2-2                  [-1, 32, 111, 111]        64\n",
+      "|    └─Mish: 2-3                         [-1, 32, 111, 111]        --\n",
+      "├─ModuleList: 1                          []                        --\n",
+      "|    └─MBConvBlock: 2-4                  [-1, 16, 111, 111]        --\n",
+      "|    |    └─Sequential: 3-1              [-1, 32, 111, 111]        352\n",
+      "|    |    └─Sequential: 3-2              [-1, 32, 111, 111]        552\n",
+      "|    |    └─Sequential: 3-3              [-1, 16, 111, 111]        544\n",
+      "|    └─MBConvBlock: 2-5                  [-1, 24, 55, 55]          --\n",
+      "|    |    └─Sequential: 3-4              [-1, 96, 111, 111]        1,728\n",
+      "|    |    └─Sequential: 3-5              [-1, 96, 55, 55]          1,056\n",
+      "|    |    └─Sequential: 3-6              [-1, 96, 55, 55]          4,728\n",
+      "|    |    └─Sequential: 3-7              [-1, 24, 55, 55]          2,352\n",
+      "|    └─MBConvBlock: 2-6                  [-1, 24, 55, 55]          --\n",
+      "|    |    └─Sequential: 3-8              [-1, 144, 55, 55]         3,744\n",
+      "|    |    └─Sequential: 3-9              [-1, 144, 55, 55]         1,584\n",
+      "|    |    └─Sequential: 3-10             [-1, 144, 55, 55]         10,548\n",
+      "|    |    └─Sequential: 3-11             [-1, 24, 55, 55]          3,504\n",
+      "|    └─MBConvBlock: 2-7                  [-1, 40, 27, 27]          --\n",
+      "|    |    └─Sequential: 3-12             [-1, 144, 55, 55]         3,744\n",
+      "|    |    └─Sequential: 3-13             [-1, 144, 27, 27]         3,888\n",
+      "|    |    └─Sequential: 3-14             [-1, 144, 27, 27]         10,548\n",
+      "|    |    └─Sequential: 3-15             [-1, 40, 27, 27]          5,840\n",
+      "|    └─MBConvBlock: 2-8                  [-1, 40, 27, 27]          --\n",
+      "|    |    └─Sequential: 3-16             [-1, 240, 27, 27]         10,080\n",
+      "|    |    └─Sequential: 3-17             [-1, 240, 27, 27]         6,480\n",
+      "|    |    └─Sequential: 3-18             [-1, 240, 27, 27]         29,100\n",
+      "|    |    └─Sequential: 3-19             [-1, 40, 27, 27]          9,680\n",
+      "|    └─MBConvBlock: 2-9                  [-1, 80, 13, 13]          --\n",
+      "|    |    └─Sequential: 3-20             [-1, 240, 27, 27]         10,080\n",
+      "|    |    └─Sequential: 3-21             [-1, 240, 13, 13]         2,640\n",
+      "|    |    └─Sequential: 3-22             [-1, 240, 13, 13]         29,100\n",
+      "|    |    └─Sequential: 3-23             [-1, 80, 13, 13]          19,360\n",
+      "|    └─MBConvBlock: 2-10                 [-1, 80, 13, 13]          --\n",
+      "|    |    └─Sequential: 3-24             [-1, 480, 13, 13]         39,360\n",
+      "|    |    └─Sequential: 3-25             [-1, 480, 13, 13]         5,280\n",
+      "|    |    └─Sequential: 3-26             [-1, 480, 13, 13]         115,800\n",
+      "|    |    └─Sequential: 3-27             [-1, 80, 13, 13]          38,560\n",
+      "|    └─MBConvBlock: 2-11                 [-1, 80, 13, 13]          --\n",
+      "|    |    └─Sequential: 3-28             [-1, 480, 13, 13]         39,360\n",
+      "|    |    └─Sequential: 3-29             [-1, 480, 13, 13]         5,280\n",
+      "|    |    └─Sequential: 3-30             [-1, 480, 13, 13]         115,800\n",
+      "|    |    └─Sequential: 3-31             [-1, 80, 13, 13]          38,560\n",
+      "|    └─MBConvBlock: 2-12                 [-1, 112, 13, 13]         --\n",
+      "|    |    └─Sequential: 3-32             [-1, 480, 13, 13]         39,360\n",
+      "|    |    └─Sequential: 3-33             [-1, 480, 13, 13]         12,960\n",
+      "|    |    └─Sequential: 3-34             [-1, 480, 13, 13]         115,800\n",
+      "|    |    └─Sequential: 3-35             [-1, 112, 13, 13]         53,984\n",
+      "|    └─MBConvBlock: 2-13                 [-1, 112, 13, 13]         --\n",
+      "|    |    └─Sequential: 3-36             [-1, 672, 13, 13]         76,608\n",
+      "|    |    └─Sequential: 3-37             [-1, 672, 13, 13]         18,144\n",
+      "|    |    └─Sequential: 3-38             [-1, 672, 13, 13]         226,632\n",
+      "|    |    └─Sequential: 3-39             [-1, 112, 13, 13]         75,488\n",
+      "|    └─MBConvBlock: 2-14                 [-1, 112, 13, 13]         --\n",
+      "|    |    └─Sequential: 3-40             [-1, 672, 13, 13]         76,608\n",
+      "|    |    └─Sequential: 3-41             [-1, 672, 13, 13]         18,144\n",
+      "|    |    └─Sequential: 3-42             [-1, 672, 13, 13]         226,632\n",
+      "|    |    └─Sequential: 3-43             [-1, 112, 13, 13]         75,488\n",
+      "|    └─MBConvBlock: 2-15                 [-1, 192, 6, 6]           --\n",
+      "|    |    └─Sequential: 3-44             [-1, 672, 13, 13]         76,608\n",
+      "|    |    └─Sequential: 3-45             [-1, 672, 6, 6]           18,144\n",
+      "|    |    └─Sequential: 3-46             [-1, 672, 6, 6]           226,632\n",
+      "|    |    └─Sequential: 3-47             [-1, 192, 6, 6]           129,408\n",
+      "|    └─MBConvBlock: 2-16                 [-1, 192, 6, 6]           --\n",
+      "|    |    └─Sequential: 3-48             [-1, 1152, 6, 6]          223,488\n",
+      "|    |    └─Sequential: 3-49             [-1, 1152, 6, 6]          31,104\n",
+      "|    |    └─Sequential: 3-50             [-1, 1152, 6, 6]          664,992\n",
+      "|    |    └─Sequential: 3-51             [-1, 192, 6, 6]           221,568\n",
+      "|    └─MBConvBlock: 2-17                 [-1, 192, 6, 6]           --\n",
+      "|    |    └─Sequential: 3-52             [-1, 1152, 6, 6]          223,488\n",
+      "|    |    └─Sequential: 3-53             [-1, 1152, 6, 6]          31,104\n",
+      "|    |    └─Sequential: 3-54             [-1, 1152, 6, 6]          664,992\n",
+      "|    |    └─Sequential: 3-55             [-1, 192, 6, 6]           221,568\n",
+      "|    └─MBConvBlock: 2-18                 [-1, 192, 6, 6]           --\n",
+      "|    |    └─Sequential: 3-56             [-1, 1152, 6, 6]          223,488\n",
+      "|    |    └─Sequential: 3-57             [-1, 1152, 6, 6]          31,104\n",
+      "|    |    └─Sequential: 3-58             [-1, 1152, 6, 6]          664,992\n",
+      "|    |    └─Sequential: 3-59             [-1, 192, 6, 6]           221,568\n",
+      "|    └─MBConvBlock: 2-19                 [-1, 320, 6, 6]           --\n",
+      "|    |    └─Sequential: 3-60             [-1, 1152, 6, 6]          223,488\n",
+      "|    |    └─Sequential: 3-61             [-1, 1152, 6, 6]          12,672\n",
+      "|    |    └─Sequential: 3-62             [-1, 1152, 6, 6]          664,992\n",
+      "|    |    └─Sequential: 3-63             [-1, 320, 6, 6]           369,280\n",
+      "├─Sequential: 1-2                        [-1, 1280, 6, 6]          --\n",
+      "|    └─Conv2d: 2-20                      [-1, 1280, 6, 6]          409,600\n",
+      "|    └─BatchNorm2d: 2-21                 [-1, 1280, 6, 6]          2,560\n",
+      "==========================================================================================\n",
+      "Total params: 7,142,272\n",
+      "Trainable params: 7,142,272\n",
+      "Non-trainable params: 0\n",
+      "Total mult-adds (M): 657.05\n",
+      "==========================================================================================\n",
+      "Input size (MB): 0.19\n",
+      "Forward/backward pass size (MB): 115.14\n",
+      "Params size (MB): 27.25\n",
+      "Estimated Total Size (MB): 142.58\n",
+      "==========================================================================================\n"
+     ]
+    }
+   ],
+   "source": [
+    "summary(en, (1, 224, 224));"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 54,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(2, 2)"
+      ]
+     },
+     "execution_count": 54,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "(2,) * 2"
+   ]
+  },
+  {
+   "cell_type": "code",
    "execution_count": 4,
    "metadata": {},
    "outputs": [
     {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/aktersnurra/.cache/pypoetry/virtualenvs/text-recognizer-ejNaVa9M-py3.9/lib/python3.9/site-packages/torch/cuda/__init__.py:52: UserWarning: CUDA initialization: CUDA unknown error - this may be due to an incorrectly set up environment, e.g. changing env variable CUDA_VISIBLE_DEVICES after program start. Setting the available devices to be zero. (Triggered internally at  /pytorch/c10/cuda/CUDAFunctions.cpp:115.)\n",
+      "  return torch._C._cuda_getDeviceCount() > 0\n"
+     ]
+    },
+    {
      "data": {
       "text/plain": [
-       "True"
+       "False"
       ]
      },
      "execution_count": 4,
@@ -195,21 +353,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "ename": "ModuleNotFoundError",
-     "evalue": "No module named 'text_recognizer.networks.encoders.efficientnet.efficientnet'",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mModuleNotFoundError\u001b[0m                       Traceback (most recent call last)",
-      "\u001b[0;32m<ipython-input-6-c209d858dfb1>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0;32mfrom\u001b[0m \u001b[0mtext_recognizer\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mnetworks\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mencoders\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mefficientnet\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mefficientnet\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mEfficientNet\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
-      "\u001b[0;31mModuleNotFoundError\u001b[0m: No module named 'text_recognizer.networks.encoders.efficientnet.efficientnet'"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "from text_recognizer.networks.encoders.efficientnet.efficientnet import EfficientNet"
    ]