PR BY Binu Raj E

Projects/Projects list/Project 0/README.md

@@ -1,11 +1,11 @@
-# Project Name
-Project description
+# Medical x-ray detection using cnn
+   Prediction of x-ray chest to tell it's normal or pneumonia affected.
 
 # What will you learn
-By doing this project you will learn how to build...
+This project much good in learning CNN application and it's a good project to showcase
 
 # Dataset for the project
-About the dataset and how to download it
+Dataset used in this project is taken from kaggle and I used Kaggle API to connect Json file downloaded to authorize connection of dataset to Google colab.The dataset contain normal and pneumonia affected X-ray images,using this apply CNN to predict whether given X-ray is Normal or not.
 
 # What algorithms and frameworks you could use
 Suggestion for algorithms and tools to use to do the project

Projects/Projects list/Project 0/test_project_xray.ipynb

@@ -0,0 +1,75 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "name": "test project xray.ipynb",
+      "provenance": [],
+      "collapsed_sections": []
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "_t4OZ9M4Ll1m"
+      },
+      "source": [
+        "import numpy as np\n"
+      ],
+      "execution_count": 4,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 231
+        },
+        "id": "av141GiALqcy",
+        "outputId": "1684788d-63c5-489b-d7ee-27db751cdbe9"
+      },
+      "source": [
+        "# Testing with sample Chest X-Ray\n",
+        "hardik_path = '/content/download.jpeg'\n",
+        "from tensorflow.keras.preprocessing import image\n",
+        "hardik_img = image.load_img(hardik_path, target_size=(500, 500),color_mode='grayscale')# Preprocessing the image\n",
+        "pp_hardik_img = image.img_to_array(hardik_img)\n",
+        "pp_hardik_img = pp_hardik_img/255\n",
+        "pp_hardik_img = np.expand_dims(pp_hardik_img, axis=0)#predict\n",
+        "hardik_preds= cnn.predict(pp_hardik_img)#print\n",
+        "plt.figure(figsize=(6,6))\n",
+        "plt.axis('off')\n",
+        "if hardik_preds>= 0.5: \n",
+        "    out = ('I am {:.2%} percent confirmed that this is a Pneumonia case'.format(hardik_preds[0][0]))\n",
+        "    \n",
+        "else: \n",
+        "   out = ('I am {:.2%} percent confirmed that this is a Normal case'.format(1-hardik_preds[0][0]))\n",
+        "plt.imshow(np.squeeze(pp_hardik_img))\n",
+        "plt.show()"
+      ],
+      "execution_count": 5,
+      "outputs": [
+        {
+          "output_type": "error",
+          "ename": "NameError",
+          "evalue": "ignored",
+          "traceback": [
+            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+            "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
+            "\u001b[0;32m<ipython-input-5-bb93a755dcbb>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      6\u001b[0m \u001b[0mpp_hardik_img\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpp_hardik_img\u001b[0m\u001b[0;34m/\u001b[0m\u001b[0;36m255\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      7\u001b[0m \u001b[0mpp_hardik_img\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mexpand_dims\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mpp_hardik_img\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;31m#predict\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 8\u001b[0;31m \u001b[0mhardik_preds\u001b[0m\u001b[0;34m=\u001b[0m \u001b[0mcnn\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpredict\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mpp_hardik_img\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;31m#print\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      9\u001b[0m \u001b[0mplt\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfigure\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfigsize\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m6\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;36m6\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     10\u001b[0m \u001b[0mplt\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0maxis\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'off'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+            "\u001b[0;31mNameError\u001b[0m: name 'cnn' is not defined"
+          ]
+        }
+      ]
+    }
+  ]
+}

Tasks/Binu/Day_3_task.ipynb

@@ -0,0 +1,162 @@
+{
+  "nbformat": 4,
+  "nbformat_minor": 0,
+  "metadata": {
+    "colab": {
+      "name": "Day 3 task.ipynb",
+      "provenance": []
+    },
+    "kernelspec": {
+      "name": "python3",
+      "display_name": "Python 3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "cells": [
+    {
+      "cell_type": "code",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "_7y2KboYO0wK",
+        "outputId": "8346f8cc-4819-4de7-b3d5-fa5b0cd96301"
+      },
+      "source": [
+        "pip install -q -U tensorflow-text"
+      ],
+      "execution_count": 1,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "\u001b[K     |████████████████████████████████| 4.4 MB 4.3 MB/s \n",
+            "\u001b[?25h"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "tPFEUKXqOgxT"
+      },
+      "source": [
+        "import tensorflow as tf\n",
+        "import tensorflow_text as text\n",
+        "import functools\n",
+        "import pathlib\n",
+        "import collections\n",
+        "import re\n",
+        "import string\n",
+        "\n",
+        "from tensorflow.keras import layers\n",
+        "from tensorflow.keras import losses\n",
+        "from tensorflow.keras import preprocessing\n",
+        "from tensorflow.keras import utils\n",
+        "from tensorflow.keras.layers.experimental.preprocessing import TextVectorization\n",
+        "\n",
+        "import tensorflow_datasets as tfds"
+      ],
+      "execution_count": 2,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "x6hxZff8O6G0",
+        "outputId": "5b2a2b09-3ea6-452c-b07d-870b5ed1bf45"
+      },
+      "source": [
+        "directory_url = 'https://storage.googleapis.com/download.tensorflow.org/data/illiad/'\n",
+        "file_names = ['cowper.txt', 'derby.txt', 'butler.txt']\n",
+        "\n",
+        "#for name in FILE_NAMES:\n",
+        "  #text_dir = utils.get_file(name, origin=DIRECTORY_URL + name)\n",
+        "\n",
+        "#parent_dir = pathlib.Path(text_dir).parent\n",
+        "#list(parent_dir.iterdir())\n",
+        "\n",
+        "file_paths = [\n",
+        "    tf.keras.utils.get_file(file_name, directory_url + file_name)\n",
+        "    for file_name in file_names\n",
+        "]\n",
+        "\n",
+        "dataset = tf.data.TextLineDataset(file_paths)\n",
+        "for line in dataset.take(5):\n",
+        "  print(line.numpy())\n"
+      ],
+      "execution_count": 3,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Downloading data from https://storage.googleapis.com/download.tensorflow.org/data/illiad/cowper.txt\n",
+            "819200/815980 [==============================] - 0s 0us/step\n",
+            "827392/815980 [==============================] - 0s 0us/step\n",
+            "Downloading data from https://storage.googleapis.com/download.tensorflow.org/data/illiad/derby.txt\n",
+            "811008/809730 [==============================] - 0s 0us/step\n",
+            "819200/809730 [==============================] - 0s 0us/step\n",
+            "Downloading data from https://storage.googleapis.com/download.tensorflow.org/data/illiad/butler.txt\n",
+            "811008/807992 [==============================] - 0s 0us/step\n",
+            "819200/807992 [==============================] - 0s 0us/step\n",
+            "b\"\\xef\\xbb\\xbfAchilles sing, O Goddess! Peleus' son;\"\n",
+            "b'His wrath pernicious, who ten thousand woes'\n",
+            "b\"Caused to Achaia's host, sent many a soul\"\n",
+            "b'Illustrious into Ades premature,'\n",
+            "b'And Heroes gave (so stood the will of Jove)'\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "Tw_cGtrfmMWg",
+        "outputId": "d600c40e-f0f7-4c96-a0e1-8df30f1df534"
+      },
+      "source": [
+        "dataset = tf.data.TextLineDataset(file_paths)\n",
+        "for line in dataset.take(5):\n",
+        "  print(line.numpy().decode(\"utf-8\"))"
+      ],
+      "execution_count": 6,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Achilles sing, O Goddess! Peleus' son;\n",
+            "His wrath pernicious, who ten thousand woes\n",
+            "Caused to Achaia's host, sent many a soul\n",
+            "Illustrious into Ades premature,\n",
+            "And Heroes gave (so stood the will of Jove)\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "metadata": {
+        "id": "TUQOFwdfRTQy"
+      },
+      "source": [
+        "text.normalize_utf8(\n",
+        "    input, normalization_form='NFKC', name=None\n",
+        ")"
+      ],
+      "execution_count": null,
+      "outputs": []
+    }
+  ]
+}

Tasks/Binu/task_5_tinkerhub.py

@@ -0,0 +1,94 @@
+# -*- coding: utf-8 -*-
+"""task 5 tinkerhub.ipynb
+
+Automatically generated by Colaboratory.
+
+Original file is located at
+    https://colab.research.google.com/drive/1nCcARJPP5je46FNNBR_M0ccHif_Xm2LL
+"""
+
+from tensorflow.keras import layers
+from tensorflow.keras import models
+import tensorflow_datasets as tfds
+from tensorflow.keras.datasets import mnist
+from tensorflow.keras.utils import to_categorical
+import tensorflow as tf
+import matplotlib.pyplot as plt
+from tensorflow.keras.callbacks import EarlyStopping
+import math
+
+import tensorflow.keras.backend as K
+import numpy as np
+
+
+
+from tensorflow.keras.callbacks import LambdaCallback
+
+
+from lrfinder import LRFinder
+
+(ds_train, ds_test), ds_info = tfds.load(
+    'mnist',
+    split=['train', 'test'],
+    shuffle_files=True,
+    as_supervised=True,
+    with_info=True,
+)
+
+def normalize_img(image, label):
+  """Normalizes images: `uint8` -> `float32`."""
+  return tf.cast(image, tf.float32) / 255., label
+
+ds_train = ds_train.map(
+    normalize_img, num_parallel_calls=tf.data.experimental.AUTOTUNE)
+ds_train = ds_train.cache()
+ds_train = ds_train.shuffle(ds_info.splits['train'].num_examples)
+ds_train = ds_train.batch(128)
+ds_train = ds_train.prefetch(tf.data.experimental.AUTOTUNE)
+
+ds_test = ds_test.map(
+    normalize_img, num_parallel_calls=tf.data.experimental.AUTOTUNE)
+ds_test = ds_test.batch(128)
+ds_test = ds_test.cache()
+ds_test = ds_test.prefetch(tf.data.experimental.AUTOTUNE)
+
+model = tf.keras.models.Sequential([
+  tf.keras.layers.Flatten(input_shape=(28, 28)),
+  tf.keras.layers.Dense(128,activation='relu'),
+  tf.keras.layers.Dense(10)
+])
+
+model.compile(
+    optimizer=tf.keras.optimizers.Adam(0.001),
+    loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
+    metrics=[tf.keras.metrics.SparseCategoricalAccuracy()],
+)
+
+BATCH = 128
+
+lr_finder = LRFinder(model)
+STEPS_PER_EPOCH = np.ceil(len(ds_train) / BATCH)
+lr_finder.find(ds_train, start_lr=1e-6, end_lr=1, epochs=5,
+               steps_per_epoch=STEPS_PER_EPOCH)
+learning_rates = lr_finder.get_learning_rates()
+losses = lr_finder.get_losses()
+best_lr = lr_finder.get_best_lr(sma=20)
+print(best_lr)
+K.set_value(model.optimizer.lr, best_lr)
+
+def plot_loss(learning_rates, losses, n_skip_beginning=10, n_skip_end=5, x_scale='log'):
+    f, ax = plt.subplots()
+    ax.set_ylabel("loss")
+    ax.set_xlabel("learning rate (log scale)")
+    ax.plot(learning_rates[n_skip_beginning:-n_skip_end],
+            losses[n_skip_beginning:-n_skip_end])
+    ax.set_xscale(x_scale)
+    return(ax)
+
+axs = plot_loss(learning_rates, losses)
+axs.axvline(x=lr_finder.get_best_lr(sma=20), c='r', linestyle='-.')
+plt.show()
+earlystop_callback = EarlyStopping(
+    monitor='val_loss', min_delta=0, patience=3)
+
+history = model.fit(ds_train, epochs=10, validation_data=ds_test, callbacks=[earlystop_callback])