G

Co-Authored-By: Ranuga <[email protected]>

Author: Programmer-RD-AI

.ipynb_checkpoints/Theory_03-checkpoint.ipynb

@@ -0,0 +1,63 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "d2a7fee3-2187-47bd-9bd1-728eb967c92f",
+   "metadata": {},
+   "source": [
+    "# CNN\n",
+    "\n",
+    "A type artifical neural network, it has convolutional and non covolutional layers\n",
+    "\n",
+    "There are many filters in the convolutional layers and they have specific tasks of detecting certain parts of the image for example textures, edges, etc...\n",
+    "\n",
+    "Essentially there is filter where it goes over the image this is the kernal size then it produces a product of the output and this happens over and over again, the weights and bias of the filter is what is changed overtime"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "fcf29831-9d66-4746-8da0-17b93e5c0da9",
+   "metadata": {},
+   "source": [
+    "# Max Pool\n",
+    "\n",
+    "Reduces the no. of pixels\n",
+    "\n",
+    "We give a filter size, the stride is how many pixels the filter moves\n",
+    "\n",
+    "From every filter uses it takes the highest one  \n",
+    "\n",
+    "Its helful becz it reduces parameters() and computational needs and reduce over fitting, this is due to a sort of generalisation "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2953d201-aede-45ad-9607-d9f1081dbdde",
+   "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": "3.8.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

.virtual_documents/Theory_03.ipynb.py

@@ -0,0 +1 @@
+

Theory_03.ipynb

@@ -0,0 +1,63 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "d2a7fee3-2187-47bd-9bd1-728eb967c92f",
+   "metadata": {},
+   "source": [
+    "# CNN\n",
+    "\n",
+    "A type artifical neural network, it has convolutional and non covolutional layers\n",
+    "\n",
+    "There are many filters in the convolutional layers and they have specific tasks of detecting certain parts of the image for example textures, edges, etc...\n",
+    "\n",
+    "Essentially there is filter where it goes over the image this is the kernal size then it produces a product of the output and this happens over and over again, the weights and bias of the filter is what is changed overtime"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "fcf29831-9d66-4746-8da0-17b93e5c0da9",
+   "metadata": {},
+   "source": [
+    "# Max Pool\n",
+    "\n",
+    "Reduces the no. of pixels\n",
+    "\n",
+    "We give a filter size, the stride is how many pixels the filter moves\n",
+    "\n",
+    "From every filter uses it takes the highest one  \n",
+    "\n",
+    "Its helful becz it reduces parameters() and computational needs and reduce over fitting, this is due to a sort of generalisation "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2953d201-aede-45ad-9607-d9f1081dbdde",
+   "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": "3.8.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}