heuzef
/
jan24_cds_mushrooms
1
0
Fork 0
Code Issues 0 Pull Requests 0 Releases 0 Wiki Activity
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
3 Commits
1 Branch
332 MiB
 
 
 
Branch: master
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'master'
${ noResults }
jan24_cds_mushrooms/notebooks/JarviSpore/Base_JarviSpore.ipynb

621 lines
43 KiB
Raw Permalink Blame History 

  1. {

  2.  "cells": [

  3.   {

  4.    "cell_type": "code",

  5.    "execution_count": 1,

  6.    "metadata": {},

  7.    "outputs": [

  8.     {

  9.      "name": "stderr",

  10.      "output_type": "stream",

  11.      "text": [

  12.       "2024-10-25 11:03:35.818798: I external/local_xla/xla/tsl/cuda/cudart_stub.cc:32] Could not find cuda drivers on your machine, GPU will not be used.\n",

  13.       "2024-10-25 11:03:35.931633: I external/local_xla/xla/tsl/cuda/cudart_stub.cc:32] Could not find cuda drivers on your machine, GPU will not be used.\n",

  14.       "2024-10-25 11:03:35.978295: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:485] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n",

  15.       "2024-10-25 11:03:36.074794: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:8454] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n",

  16.       "2024-10-25 11:03:36.095882: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1452] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n",

  17.       "2024-10-25 11:03:36.215087: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",

  18.       "To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n",

  19.       "2024-10-25 11:03:37.495041: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT\n"

  20.      ]

  21.     }

  22.    ],

  23.    "source": [

  24.     "import os\n",

  25.     "import numpy as np\n",

  26.     "import tensorflow as tf\n",

  27.     "import matplotlib\n",

  28.     "import matplotlib.pyplot as plt\n",

  29.     "import cv2\n",

  30.     "import pandas as pd\n",

  31.     "import numpy as np\n",

  32.     "import mlflow\n",

  33.     "from tensorflow.keras import layers, models\n",

  34.     "from tensorflow.keras.preprocessing import image_dataset_from_directory\n",

  35.     "from tensorflow.keras.models import Model\n",

  36.     "from sklearn.metrics import classification_report\n",

  37.     "from PIL import Image\n",

  38.     "from sklearn.metrics import confusion_matrix\n",

  39.     "from sklearn.metrics import ConfusionMatrixDisplay\n",

  40.     "from sklearn import __version__ as sklearn_version"

  41.    ]

  42.   },

  43.   {

  44.    "cell_type": "code",

  45.    "execution_count": 2,

  46.    "metadata": {},

  47.    "outputs": [

  48.     {

  49.      "data": {

  50.       "text/plain": [

  51.        "<Experiment: artifact_location='mlflow-artifacts:/103379370584144202', creation_time=1721579566179, experiment_id='103379370584144202', last_update_time=1721579566179, lifecycle_stage='active', name='champi', tags={'mlflow.sharedViewState.d4d3ab312f340bdf78e73ff3b2e223651ae813cd5c2bb0ee7938c7dba4de2511': '{\"searchFilter\":\"\",\"orderByKey\":\"attributes.start_time\",\"orderByAsc\":false,\"startTime\":\"ALL\",\"lifecycleFilter\":\"Active\",\"datasetsFilter\":[],\"modelVersionFilter\":\"All '\n",

  52.        "                                                                                            'Runs\",\"selectedColumns\":[\"attributes.`Models`\",\"metrics.`accuracy`\",\"metrics.`val_accuracy`\",\"attributes.`User`\",\"params.`epochs`\",\"attributes.`Description`\"],\"runsExpanded\":{},\"runsPinned\":[],\"runsHidden\":[],\"runsHiddenMode\":\"FIRST_10_RUNS\",\"compareRunCharts\":[{\"uuid\":\"17218375793866mexilt9\",\"type\":\"BAR\",\"runsCountToCompare\":10,\"metricSectionId\":\"17218375793869x5p8wdz\",\"deleted\":false,\"isGenerated\":true,\"metricKey\":\"train_accuracy\"},{\"uuid\":\"172183757938670qjdu0z\",\"type\":\"BAR\",\"runsCountToCompare\":10,\"metricSectionId\":\"17218375793869x5p8wdz\",\"deleted\":false,\"isGenerated\":true,\"metricKey\":\"train_loss\"},{\"uuid\":\"1721837579386s9miya0n\",\"type\":\"BAR\",\"runsCountToCompare\":10,\"metricSectionId\":\"17218375793869x5p8wdz\",\"deleted\":false,\"isGenerated\":true,\"metricKey\":\"val_accuracy\"},{\"uuid\":\"1721837579386tzl1e19r\",\"type\":\"BAR\",\"runsCountToCompare\":10,\"metricSectionId\":\"17218375793869x5p8wdz\",\"deleted\":false,\"isGenerated\":true,\"metricKey\":\"val_loss\"}],\"compareRunSections\":[{\"uuid\":\"17218375793869x5p8wdz\",\"name\":\"Model '\n",

  53.        "                                                                                            'metrics\",\"display\":true,\"isReordered\":false,\"deleted\":false,\"isGenerated\":true},{\"uuid\":\"1721837579386jrv4pstu\",\"name\":\"System '\n",

  54.        "                                                                                            'metrics\",\"display\":true,\"isReordered\":false,\"deleted\":false,\"isGenerated\":true}],\"viewMaximized\":false,\"runListHidden\":false,\"isAccordionReordered\":false,\"useGroupedValuesInCharts\":true,\"groupBy\":null,\"groupsExpanded\":{},\"autoRefreshEnabled\":false}'}>"

  55.       ]

  56.      },

  57.      "execution_count": 2,

  58.      "metadata": {},

  59.      "output_type": "execute_result"

  60.     }

  61.    ],

  62.    "source": [

  63.     "# Configuration du serveur MLflow\n",

  64.     "mlflow_server_uri = \"https://champi.heuzef.com\"\n",

  65.     "mlflow.set_tracking_uri(mlflow_server_uri)\n",

  66.     "mlflow.set_experiment(\"champi\")"

  67.    ]

  68.   },

  69.   {

  70.    "cell_type": "markdown",

  71.    "metadata": {},

  72.    "source": [

  73.     "# Test et Evaluation du Modèle"

  74.    ]

  75.   },

  76.   {

  77.    "cell_type": "code",

  78.    "execution_count": 3,

  79.    "metadata": {},

  80.    "outputs": [

  81.     {

  82.      "name": "stderr",

  83.      "output_type": "stream",

  84.      "text": [

  85.       "/home/heuzef/GIT/jan24_cds_mushrooms/.venv/lib/python3.11/site-packages/keras/src/layers/convolutional/base_conv.py:107: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n",

  86.       "  super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n",

  87.       "/home/heuzef/GIT/jan24_cds_mushrooms/.venv/lib/python3.11/site-packages/keras/src/optimizers/base_optimizer.py:33: UserWarning: Argument `decay` is no longer supported and will be ignored.\n",

  88.       "  warnings.warn(\n",

  89.       "WARNING:absl:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the model.\n",

  90.       "WARNING:absl:Error in loading the saved optimizer state. As a result, your model is starting with a freshly initialized optimizer.\n"

  91.      ]

  92.     },

  93.     {

  94.      "data": {

  95.       "text/html": [

  96.        "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"sequential\"</span>\n",

  97.        "</pre>\n"

  98.       ],

  99.       "text/plain": [

  100.        "\u001b[1mModel: \"sequential\"\u001b[0m\n"

  101.       ]

  102.      },

  103.      "metadata": {},

  104.      "output_type": "display_data"

  105.     },

  106.     {

  107.      "data": {

  108.       "text/html": [

  109.        "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",

  110.        "┃<span style=\"font-weight: bold\"> Layer (type)                    </span>┃<span style=\"font-weight: bold\"> Output Shape           </span>┃<span style=\"font-weight: bold\">       Param # </span>┃\n",

  111.        "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",

  112.        "│ conv2d (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">222</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">222</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)   │           <span style=\"color: #00af00; text-decoration-color: #00af00\">896</span> │\n",

  113.        "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",

  114.        "│ batch_normalization             │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">222</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">222</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)   │           <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span> │\n",

  115.        "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            │                        │               │\n",

  116.        "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",

  117.        "│ max_pooling2d (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)    │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">111</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">111</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)   │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",

  118.        "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",

  119.        "│ conv2d_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">109</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">109</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)   │        <span style=\"color: #00af00; text-decoration-color: #00af00\">18,496</span> │\n",

  120.        "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",

  121.        "│ batch_normalization_1           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">109</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">109</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)   │           <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span> │\n",

  122.        "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            │                        │               │\n",

  123.        "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",

  124.        "│ max_pooling2d_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)  │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">54</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">54</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)     │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",

  125.        "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",

  126.        "│ conv2d_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">52</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">52</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)    │        <span style=\"color: #00af00; text-decoration-color: #00af00\">73,856</span> │\n",

  127.        "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",

  128.        "│ batch_normalization_2           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">52</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">52</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)    │           <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span> │\n",

  129.        "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            │                        │               │\n",

  130.        "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",

  131.        "│ max_pooling2d_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)  │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">26</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">26</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)    │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",

  132.        "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",

  133.        "│ conv2d_3 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">24</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">24</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)    │       <span style=\"color: #00af00; text-decoration-color: #00af00\">295,168</span> │\n",

  134.        "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",

  135.        "│ batch_normalization_3           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">24</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">24</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)    │         <span style=\"color: #00af00; text-decoration-color: #00af00\">1,024</span> │\n",

  136.        "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            │                        │               │\n",

  137.        "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",

  138.        "│ max_pooling2d_3 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)  │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">12</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">12</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)    │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",

  139.        "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",

  140.        "│ conv2d_4 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">10</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">10</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>)    │     <span style=\"color: #00af00; text-decoration-color: #00af00\">1,180,160</span> │\n",

  141.        "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",

  142.        "│ batch_normalization_4           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">10</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">10</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>)    │         <span style=\"color: #00af00; text-decoration-color: #00af00\">2,048</span> │\n",

  143.        "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            │                        │               │\n",

  144.        "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",

  145.        "│ max_pooling2d_4 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)  │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">5</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">5</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>)      │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",

  146.        "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",

  147.        "│ flatten (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Flatten</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">12800</span>)          │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",

  148.        "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",

  149.        "│ dense (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                   │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>)            │     <span style=\"color: #00af00; text-decoration-color: #00af00\">6,554,112</span> │\n",

  150.        "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",

  151.        "│ dropout (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span>)            │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",

  152.        "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",

  153.        "│ dense_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">23</span>)             │        <span style=\"color: #00af00; text-decoration-color: #00af00\">11,799</span> │\n",

  154.        "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",

  155.        "</pre>\n"

  156.       ],

  157.       "text/plain": [

  158.        "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",

  159.        "┃\u001b[1m \u001b[0m\u001b[1mLayer (type)                   \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape          \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      Param #\u001b[0m\u001b[1m \u001b[0m┃\n",

  160.        "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",

  161.        "│ conv2d (\u001b[38;5;33mConv2D\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m222\u001b[0m, \u001b[38;5;34m222\u001b[0m, \u001b[38;5;34m32\u001b[0m)   │           \u001b[38;5;34m896\u001b[0m │\n",

  162.        "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",

  163.        "│ batch_normalization             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m222\u001b[0m, \u001b[38;5;34m222\u001b[0m, \u001b[38;5;34m32\u001b[0m)   │           \u001b[38;5;34m128\u001b[0m │\n",

  164.        "│ (\u001b[38;5;33mBatchNormalization\u001b[0m)            │                        │               │\n",

  165.        "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",

  166.        "│ max_pooling2d (\u001b[38;5;33mMaxPooling2D\u001b[0m)    │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m111\u001b[0m, \u001b[38;5;34m111\u001b[0m, \u001b[38;5;34m32\u001b[0m)   │             \u001b[38;5;34m0\u001b[0m │\n",

  167.        "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",

  168.        "│ conv2d_1 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m109\u001b[0m, \u001b[38;5;34m109\u001b[0m, \u001b[38;5;34m64\u001b[0m)   │        \u001b[38;5;34m18,496\u001b[0m │\n",

  169.        "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",

  170.        "│ batch_normalization_1           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m109\u001b[0m, \u001b[38;5;34m109\u001b[0m, \u001b[38;5;34m64\u001b[0m)   │           \u001b[38;5;34m256\u001b[0m │\n",

  171.        "│ (\u001b[38;5;33mBatchNormalization\u001b[0m)            │                        │               │\n",

  172.        "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",

  173.        "│ max_pooling2d_1 (\u001b[38;5;33mMaxPooling2D\u001b[0m)  │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m54\u001b[0m, \u001b[38;5;34m54\u001b[0m, \u001b[38;5;34m64\u001b[0m)     │             \u001b[38;5;34m0\u001b[0m │\n",

  174.        "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",

  175.        "│ conv2d_2 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m52\u001b[0m, \u001b[38;5;34m52\u001b[0m, \u001b[38;5;34m128\u001b[0m)    │        \u001b[38;5;34m73,856\u001b[0m │\n",

  176.        "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",

  177.        "│ batch_normalization_2           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m52\u001b[0m, \u001b[38;5;34m52\u001b[0m, \u001b[38;5;34m128\u001b[0m)    │           \u001b[38;5;34m512\u001b[0m │\n",

  178.        "│ (\u001b[38;5;33mBatchNormalization\u001b[0m)            │                        │               │\n",

  179.        "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",

  180.        "│ max_pooling2d_2 (\u001b[38;5;33mMaxPooling2D\u001b[0m)  │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m26\u001b[0m, \u001b[38;5;34m26\u001b[0m, \u001b[38;5;34m128\u001b[0m)    │             \u001b[38;5;34m0\u001b[0m │\n",

  181.        "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",

  182.        "│ conv2d_3 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m24\u001b[0m, \u001b[38;5;34m24\u001b[0m, \u001b[38;5;34m256\u001b[0m)    │       \u001b[38;5;34m295,168\u001b[0m │\n",

  183.        "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",

  184.        "│ batch_normalization_3           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m24\u001b[0m, \u001b[38;5;34m24\u001b[0m, \u001b[38;5;34m256\u001b[0m)    │         \u001b[38;5;34m1,024\u001b[0m │\n",

  185.        "│ (\u001b[38;5;33mBatchNormalization\u001b[0m)            │                        │               │\n",

  186.        "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",

  187.        "│ max_pooling2d_3 (\u001b[38;5;33mMaxPooling2D\u001b[0m)  │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m12\u001b[0m, \u001b[38;5;34m12\u001b[0m, \u001b[38;5;34m256\u001b[0m)    │             \u001b[38;5;34m0\u001b[0m │\n",

  188.        "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",

  189.        "│ conv2d_4 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m10\u001b[0m, \u001b[38;5;34m10\u001b[0m, \u001b[38;5;34m512\u001b[0m)    │     \u001b[38;5;34m1,180,160\u001b[0m │\n",

  190.        "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",

  191.        "│ batch_normalization_4           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m10\u001b[0m, \u001b[38;5;34m10\u001b[0m, \u001b[38;5;34m512\u001b[0m)    │         \u001b[38;5;34m2,048\u001b[0m │\n",

  192.        "│ (\u001b[38;5;33mBatchNormalization\u001b[0m)            │                        │               │\n",

  193.        "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",

  194.        "│ max_pooling2d_4 (\u001b[38;5;33mMaxPooling2D\u001b[0m)  │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m5\u001b[0m, \u001b[38;5;34m5\u001b[0m, \u001b[38;5;34m512\u001b[0m)      │             \u001b[38;5;34m0\u001b[0m │\n",

  195.        "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",

  196.        "│ flatten (\u001b[38;5;33mFlatten\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m12800\u001b[0m)          │             \u001b[38;5;34m0\u001b[0m │\n",

  197.        "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",

  198.        "│ dense (\u001b[38;5;33mDense\u001b[0m)                   │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m512\u001b[0m)            │     \u001b[38;5;34m6,554,112\u001b[0m │\n",

  199.        "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",

  200.        "│ dropout (\u001b[38;5;33mDropout\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m512\u001b[0m)            │             \u001b[38;5;34m0\u001b[0m │\n",

  201.        "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",

  202.        "│ dense_1 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m23\u001b[0m)             │        \u001b[38;5;34m11,799\u001b[0m │\n",

  203.        "└─────────────────────────────────┴────────────────────────┴───────────────┘\n"

  204.       ]

  205.      },

  206.      "metadata": {},

  207.      "output_type": "display_data"

  208.     },

  209.     {

  210.      "data": {

  211.       "text/html": [

  212.        "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">8,138,457</span> (31.05 MB)\n",

  213.        "</pre>\n"

  214.       ],

  215.       "text/plain": [

  216.        "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m8,138,457\u001b[0m (31.05 MB)\n"

  217.       ]

  218.      },

  219.      "metadata": {},

  220.      "output_type": "display_data"

  221.     },

  222.     {

  223.      "data": {

  224.       "text/html": [

  225.        "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">8,136,471</span> (31.04 MB)\n",

  226.        "</pre>\n"

  227.       ],

  228.       "text/plain": [

  229.        "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m8,136,471\u001b[0m (31.04 MB)\n"

  230.       ]

  231.      },

  232.      "metadata": {},

  233.      "output_type": "display_data"

  234.     },

  235.     {

  236.      "data": {

  237.       "text/html": [

  238.        "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">1,984</span> (7.75 KB)\n",

  239.        "</pre>\n"

  240.       ],

  241.       "text/plain": [

  242.        "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m1,984\u001b[0m (7.75 KB)\n"

  243.       ]

  244.      },

  245.      "metadata": {},

  246.      "output_type": "display_data"

  247.     },

  248.     {

  249.      "data": {

  250.       "text/html": [

  251.        "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Optimizer params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">2</span> (12.00 B)\n",

  252.        "</pre>\n"

  253.       ],

  254.       "text/plain": [

  255.        "\u001b[1m Optimizer params: \u001b[0m\u001b[38;5;34m2\u001b[0m (12.00 B)\n"

  256.       ]

  257.      },

  258.      "metadata": {},

  259.      "output_type": "display_data"

  260.     }

  261.    ],

  262.    "source": [

  263.     "# Charger le modèle\n",

  264.     "model = tf.keras.models.load_model('../../models/artifacts/yvan_jarvispore.h5')\n",

  265.     "\n",

  266.     "model.summary()"

  267.    ]

  268.   },

  269.   {

  270.    "cell_type": "code",

  271.    "execution_count": 27,

  272.    "metadata": {},

  273.    "outputs": [

  274.     {

  275.      "name": "stdout",

  276.      "output_type": "stream",

  277.      "text": [

  278.       "conv2d\n",

  279.       "batch_normalization\n",

  280.       "max_pooling2d\n",

  281.       "conv2d_1\n",

  282.       "batch_normalization_1\n",

  283.       "max_pooling2d_1\n",

  284.       "conv2d_2\n",

  285.       "batch_normalization_2\n",

  286.       "max_pooling2d_2\n",

  287.       "conv2d_3\n",

  288.       "batch_normalization_3\n",

  289.       "max_pooling2d_3\n",

  290.       "conv2d_4\n",

  291.       "batch_normalization_4\n",

  292.       "max_pooling2d_4\n",

  293.       "flatten\n",

  294.       "dense\n",

  295.       "dropout\n",

  296.       "dense_1\n"

  297.      ]

  298.     }

  299.    ],

  300.    "source": [

  301.     "# Vérifier les noms des couches du modèle\n",

  302.     "for layer in model.layers:\n",

  303.     "    print(layer.name)"

  304.    ]

  305.   },

  306.   {

  307.    "cell_type": "code",

  308.    "execution_count": 28,

  309.    "metadata": {},

  310.    "outputs": [

  311.     {

  312.      "name": "stdout",

  313.      "output_type": "stream",

  314.      "text": [

  315.       "[[[[46. 55. 10.]\n",

  316.       "   [48. 61.  5.]\n",

  317.       "   [45. 70.  4.]\n",

  318.       "   ...\n",

  319.       "   [22. 34. 10.]\n",

  320.       "   [24. 34.  9.]\n",

  321.       "   [24. 34.  7.]]\n",

  322.       "\n",

  323.       "  [[46. 63.  8.]\n",

  324.       "   [43. 68.  2.]\n",

  325.       "   [44. 71.  0.]\n",

  326.       "   ...\n",

  327.       "   [23. 38.  7.]\n",

  328.       "   [17. 32.  3.]\n",

  329.       "   [25. 39. 13.]]\n",

  330.       "\n",

  331.       "  [[46. 68.  3.]\n",

  332.       "   [42. 72.  0.]\n",

  333.       "   [42. 72.  0.]\n",

  334.       "   ...\n",

  335.       "   [17. 31.  6.]\n",

  336.       "   [18. 30.  6.]\n",

  337.       "   [18. 30.  6.]]\n",

  338.       "\n",

  339.       "  ...\n",

  340.       "\n",

  341.       "  [[57. 93.  6.]\n",

  342.       "   [53. 93.  5.]\n",

  343.       "   [55. 92. 14.]\n",

  344.       "   ...\n",

  345.       "   [40. 20. 13.]\n",

  346.       "   [54. 25. 11.]\n",

  347.       "   [74. 27.  9.]]\n",

  348.       "\n",

  349.       "  [[53. 91.  6.]\n",

  350.       "   [57. 94. 16.]\n",

  351.       "   [53. 84.  8.]\n",

  352.       "   ...\n",

  353.       "   [58. 18.  6.]\n",

  354.       "   [71. 28. 11.]\n",

  355.       "   [70. 24.  9.]]\n",

  356.       "\n",

  357.       "  [[56. 88. 12.]\n",

  358.       "   [55. 87. 11.]\n",

  359.       "   [55. 90. 10.]\n",

  360.       "   ...\n",

  361.       "   [70. 39. 19.]\n",

  362.       "   [76. 42. 17.]\n",

  363.       "   [72. 37. 15.]]]]\n"

  364.      ]

  365.     }

  366.    ],

  367.    "source": [

  368.     "img_path = 'Stropharia_ambigua.jpg'\n",

  369.     "img = tf.keras.utils.load_img(img_path, target_size=(224, 224))\n",

  370.     "img_array = tf.keras.utils.img_to_array(img)\n",

  371.     "img_array = np.expand_dims(img_array, axis=0)\n",

  372.     "# img_array /= 255.0 <= Ne pas appliquer cette normalisation !\n",

  373.     "\n",

  374.     "print(img_array)"

  375.    ]

  376.   },

  377.   {

  378.    "cell_type": "code",

  379.    "execution_count": 29,

  380.    "metadata": {},

  381.    "outputs": [

  382.     {

  383.      "name": "stdout",

  384.      "output_type": "stream",

  385.      "text": [

  386.       "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 28ms/step\n"

  387.      ]

  388.     },

  389.     {

  390.      "data": {

  391.       "text/plain": [

  392.        "array([[1.39423105e-15, 1.33577138e-09, 1.18861605e-11, 2.34543396e-13,\n",

  393.        "        1.46086858e-11, 6.81908577e-13, 1.31949776e-15, 6.21433040e-14,\n",

  394.        "        3.58152832e-03, 1.37310572e-05, 9.30511057e-10, 5.02229439e-11,\n",

  395.        "        3.02496773e-07, 1.34497757e-09, 1.17063070e-14, 1.64082564e-16,\n",

  396.        "        8.56261514e-13, 9.82579225e-14, 1.79859188e-16, 9.96404409e-01,\n",

  397.        "        5.06198165e-12, 1.81432788e-12, 1.04054815e-16]], dtype=float32)"

  398.       ]

  399.      },

  400.      "execution_count": 29,

  401.      "metadata": {},

  402.      "output_type": "execute_result"

  403.     }

  404.    ],

  405.    "source": [

  406.     "predictions = model.predict(img_array)\n",

  407.     "\n",

  408.     "predictions"

  409.    ]

  410.   },

  411.   {

  412.    "cell_type": "code",

  413.    "execution_count": 30,

  414.    "metadata": {},

  415.    "outputs": [

  416.     {

  417.      "data": {

  418.       "text/html": [

  419.        "<div>\n",

  420.        "<style scoped>\n",

  421.        "    .dataframe tbody tr th:only-of-type {\n",

  422.        "        vertical-align: middle;\n",

  423.        "    }\n",

  424.        "\n",

  425.        "    .dataframe tbody tr th {\n",

  426.        "        vertical-align: top;\n",

  427.        "    }\n",

  428.        "\n",

  429.        "    .dataframe thead th {\n",

  430.        "        text-align: right;\n",

  431.        "    }\n",

  432.        "</style>\n",

  433.        "<table border=\"1\" class=\"dataframe\">\n",

  434.        "  <thead>\n",

  435.        "    <tr style=\"text-align: right;\">\n",

  436.        "      <th></th>\n",

  437.        "      <th>0</th>\n",

  438.        "    </tr>\n",

  439.        "  </thead>\n",

  440.        "  <tbody>\n",

  441.        "    <tr>\n",

  442.        "      <th>0</th>\n",

  443.        "      <td>0.040466</td>\n",

  444.        "    </tr>\n",

  445.        "    <tr>\n",

  446.        "      <th>1</th>\n",

  447.        "      <td>0.040466</td>\n",

  448.        "    </tr>\n",

  449.        "    <tr>\n",

  450.        "      <th>2</th>\n",

  451.        "      <td>0.040466</td>\n",

  452.        "    </tr>\n",

  453.        "    <tr>\n",

  454.        "      <th>3</th>\n",

  455.        "      <td>0.040466</td>\n",

  456.        "    </tr>\n",

  457.        "    <tr>\n",

  458.        "      <th>4</th>\n",

  459.        "      <td>0.040466</td>\n",

  460.        "    </tr>\n",

  461.        "    <tr>\n",

  462.        "      <th>5</th>\n",

  463.        "      <td>0.040466</td>\n",

  464.        "    </tr>\n",

  465.        "    <tr>\n",

  466.        "      <th>6</th>\n",

  467.        "      <td>0.040466</td>\n",

  468.        "    </tr>\n",

  469.        "    <tr>\n",

  470.        "      <th>7</th>\n",

  471.        "      <td>0.040466</td>\n",

  472.        "    </tr>\n",

  473.        "    <tr>\n",

  474.        "      <th>8</th>\n",

  475.        "      <td>0.040611</td>\n",

  476.        "    </tr>\n",

  477.        "    <tr>\n",

  478.        "      <th>9</th>\n",

  479.        "      <td>0.040467</td>\n",

  480.        "    </tr>\n",

  481.        "    <tr>\n",

  482.        "      <th>10</th>\n",

  483.        "      <td>0.040466</td>\n",

  484.        "    </tr>\n",

  485.        "    <tr>\n",

  486.        "      <th>11</th>\n",

  487.        "      <td>0.040466</td>\n",

  488.        "    </tr>\n",

  489.        "    <tr>\n",

  490.        "      <th>12</th>\n",

  491.        "      <td>0.040466</td>\n",

  492.        "    </tr>\n",

  493.        "    <tr>\n",

  494.        "      <th>13</th>\n",

  495.        "      <td>0.040466</td>\n",

  496.        "    </tr>\n",

  497.        "    <tr>\n",

  498.        "      <th>14</th>\n",

  499.        "      <td>0.040466</td>\n",

  500.        "    </tr>\n",

  501.        "    <tr>\n",

  502.        "      <th>15</th>\n",

  503.        "      <td>0.040466</td>\n",

  504.        "    </tr>\n",

  505.        "    <tr>\n",

  506.        "      <th>16</th>\n",

  507.        "      <td>0.040466</td>\n",

  508.        "    </tr>\n",

  509.        "    <tr>\n",

  510.        "      <th>17</th>\n",

  511.        "      <td>0.040466</td>\n",

  512.        "    </tr>\n",

  513.        "    <tr>\n",

  514.        "      <th>18</th>\n",

  515.        "      <td>0.040466</td>\n",

  516.        "    </tr>\n",

  517.        "    <tr>\n",

  518.        "      <th>19</th>\n",

  519.        "      <td>0.109603</td>\n",

  520.        "    </tr>\n",

  521.        "    <tr>\n",

  522.        "      <th>20</th>\n",

  523.        "      <td>0.040466</td>\n",

  524.        "    </tr>\n",

  525.        "    <tr>\n",

  526.        "      <th>21</th>\n",

  527.        "      <td>0.040466</td>\n",

  528.        "    </tr>\n",

  529.        "    <tr>\n",

  530.        "      <th>22</th>\n",

  531.        "      <td>0.040466</td>\n",

  532.        "    </tr>\n",

  533.        "  </tbody>\n",

  534.        "</table>\n",

  535.        "</div>"

  536.       ],

  537.       "text/plain": [

  538.        "           0\n",

  539.        "0   0.040466\n",

  540.        "1   0.040466\n",

  541.        "2   0.040466\n",

  542.        "3   0.040466\n",

  543.        "4   0.040466\n",

  544.        "5   0.040466\n",

  545.        "6   0.040466\n",

  546.        "7   0.040466\n",

  547.        "8   0.040611\n",

  548.        "9   0.040467\n",

  549.        "10  0.040466\n",

  550.        "11  0.040466\n",

  551.        "12  0.040466\n",

  552.        "13  0.040466\n",

  553.        "14  0.040466\n",

  554.        "15  0.040466\n",

  555.        "16  0.040466\n",

  556.        "17  0.040466\n",

  557.        "18  0.040466\n",

  558.        "19  0.109603\n",

  559.        "20  0.040466\n",

  560.        "21  0.040466\n",

  561.        "22  0.040466"

  562.       ]

  563.      },

  564.      "execution_count": 30,

  565.      "metadata": {},

  566.      "output_type": "execute_result"

  567.     }

  568.    ],

  569.    "source": [

  570.     "score = tf.nn.softmax(predictions[0])\n",

  571.     "\n",

  572.     "pd.DataFrame(tf.nn.softmax(predictions[0]))"

  573.    ]

  574.   },

  575.   {

  576.    "cell_type": "code",

  577.    "execution_count": 31,

  578.    "metadata": {},

  579.    "outputs": [

  580.     {

  581.      "name": "stdout",

  582.      "output_type": "stream",

  583.      "text": [

  584.       "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 43ms/step\n",

  585.       "Classe prédite : 19\n"

  586.      ]

  587.     }

  588.    ],

  589.    "source": [

  590.     "# Faire la prédiction\n",

  591.     "predictions = model.predict(img_array)\n",

  592.     "\n",

  593.     "# Afficher la classe prédite (ou la distribution des probabilités)\n",

  594.     "predicted_class = np.argmax(predictions[0])  # Si le modèle a une sortie par classe\n",

  595.     "print(f'Classe prédite : {predicted_class}')"

  596.    ]

  597.   }

  598.  ],

  599.  "metadata": {

  600.   "kernelspec": {

  601.    "display_name": "jarvis_env",

  602.    "language": "python",

  603.    "name": "python3"

  604.   },

  605.   "language_info": {

  606.    "codemirror_mode": {

  607.     "name": "ipython",

  608.     "version": 3

  609.    },

  610.    "file_extension": ".py",

  611.    "mimetype": "text/x-python",

  612.    "name": "python",

  613.    "nbconvert_exporter": "python",

  614.    "pygments_lexer": "ipython3",

  615.    "version": "3.11.9"

  616.   }

  617.  },

  618.  "nbformat": 4,

  619.  "nbformat_minor": 2

  620. }