w2

BilletesMexico/weights/checkpoint

@@ -1,2 +1,2 @@
-model_checkpoint_path: "weights"
-all_model_checkpoint_paths: "weights"
+model_checkpoint_path: "weights2"
+all_model_checkpoint_paths: "weights2"

BilletesMexico/weights/weights2.data-00000-of-00001

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b60e3f0c28466e1395942cde7827c958fb3c0fa444340fa699aaf69febbda0c2
+size 97943034

billetes.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
@@ -19,7 +19,6 @@
     "import matplotlib.pyplot as plt\n",
     "import matplotlib.image as mpimg\n",
     "import numpy as np\n",
-    "import tensorflow as tf\n",
     "from tensorflow import keras\n",
     "from tensorflow.keras import layers\n",
     "import numpy as np\n",
@@ -27,14 +26,15 @@
     "import os\n",
     "from IPython.display import clear_output\n",
     "import PIL.Image as Image\n",
-    "print(tf.version.VERSION)\n",
-    "\n",
-    "\n"
+    "import tensorflow as tf\n",
+    "import tensorflow_hub as hub\n",
+    "from tensorflow.keras import layers\n",
+    "print(tf.version.VERSION)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -49,17 +49,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Found 395 files belonging to 5 classes.\n",
-      "Using 316 files for training.\n",
-      "Found 395 files belonging to 5 classes.\n",
-      "Using 79 files for validation.\n"
+      "Found 17907 files belonging to 5 classes.\n",
+      "Using 14326 files for training.\n",
+      "Found 17907 files belonging to 5 classes.\n",
+      "Using 3581 files for validation.\n"
      ]
     }
    ],
@@ -85,7 +85,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [
     {
@@ -105,7 +105,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -116,20 +116,25 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
-    "import tensorflow as tf\n",
-    "import tensorflow_hub as hub\n",
-    "from tensorflow.keras import layers\n",
+    "\n",
     "movilenet =hub.KerasLayer('https://tfhub.dev/google/tf2-preview/mobilenet_v2/feature_vector/4')\n",
     "movilenet.trainable=False\n"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# modelo 1"
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [
     {
@@ -140,36 +145,31 @@
       "_________________________________________________________________\n",
       " Layer (type)                Output Shape              Param #   \n",
       "=================================================================\n",
-      " random_flip (RandomFlip)    (None, 224, 224, 3)       0         \n",
-      "                                                                 \n",
-      " random_rotation (RandomRota  (None, 224, 224, 3)      0         \n",
-      " tion)                                                           \n",
-      "                                                                 \n",
-      " random_contrast (RandomCont  (None, 224, 224, 3)      0         \n",
-      " rast)                                                           \n",
+      " keras_layer (KerasLayer)    (None, 1001)              23853833  \n",
       "                                                                 \n",
-      " random_zoom (RandomZoom)    (None, 224, 224, 3)       0         \n",
+      " dense (Dense)               (None, 200)               200400    \n",
       "                                                                 \n",
-      " keras_layer_1 (KerasLayer)  (None, 1001)              3540265   \n",
-      "                                                                 \n",
-      " dense (Dense)               (None, 5)                 5010      \n",
+      " dense_1 (Dense)             (None, 5)                 1005      \n",
       "                                                                 \n",
       "=================================================================\n",
-      "Total params: 3,545,275\n",
-      "Trainable params: 5,010\n",
-      "Non-trainable params: 3,540,265\n",
+      "Total params: 24,055,238\n",
+      "Trainable params: 201,405\n",
+      "Non-trainable params: 23,853,833\n",
       "_________________________________________________________________\n"
      ]
     }
    ],
    "source": [
-    "model = tf.keras.Sequential([layers.RandomFlip(\"horizontal_and_vertical\"),\n",
-    "                            layers.RandomRotation(0.2),\n",
-    "                            layers.RandomContrast(.2),\n",
+    "model = tf.keras.Sequential([\n",
+    "                            #layers.RandomFlip(\"horizontal_and_vertical\"),\n",
+    "                            #layers.RandomRotation(0.2),\n",
+    "                            #layers.RandomContrast(.2),\n",
     "                            #layers.RandomBrightness(.2),\n",
-    "                            layers.RandomZoom(.2),\n",
-    "                            hub.KerasLayer(\"https://tfhub.dev/google/tf2-preview/mobilenet_v2/classification/4\", output_shape=[1001]),\n",
+    "                            #layers.RandomZoom(.2),\n",
+    "                           # hub.KerasLayer(\"https://tfhub.dev/google/tf2-preview/mobilenet_v2/classification/4\", output_shape=[1001],trainable=False),\n",
+    "                            hub.KerasLayer(\"https://tfhub.dev/google/imagenet/inception_v3/classification/5\",trainable=False),\n",
     "                            #movilenet,\n",
+    "                            tf.keras.layers.Dense(int(1001/num_classes)),\n",
     "                            tf.keras.layers.Dense(num_classes)\n",
     "                           \n",
     "\n",
@@ -182,7 +182,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 13,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -216,7 +216,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 14,
    "metadata": {},
    "outputs": [
     {
@@ -224,74 +224,74 @@
      "output_type": "stream",
      "text": [
       "Epoch 1/30\n",
-      "3/3 [==============================] - 9s 921ms/step - loss: 2.4682 - acc: 0.2437 - val_loss: 2.2278 - val_acc: 0.2278\n",
+      "112/112 [==============================] - 51s 342ms/step - loss: 0.7923 - acc: 0.7865 - val_loss: 0.4684 - val_acc: 0.8472\n",
       "Epoch 2/30\n",
-      "3/3 [==============================] - 1s 149ms/step - loss: 1.6423 - acc: 0.3671 - val_loss: 1.9007 - val_acc: 0.3418\n",
+      "112/112 [==============================] - 33s 292ms/step - loss: 0.4040 - acc: 0.8689 - val_loss: 0.3798 - val_acc: 0.8741\n",
       "Epoch 3/30\n",
-      "3/3 [==============================] - 1s 151ms/step - loss: 1.1681 - acc: 0.5570 - val_loss: 1.3871 - val_acc: 0.4684\n",
+      "112/112 [==============================] - 33s 291ms/step - loss: 0.3405 - acc: 0.8910 - val_loss: 0.3805 - val_acc: 0.8735\n",
       "Epoch 4/30\n",
-      "3/3 [==============================] - 1s 151ms/step - loss: 0.7328 - acc: 0.7563 - val_loss: 1.0329 - val_acc: 0.6203\n",
+      "112/112 [==============================] - 33s 291ms/step - loss: 0.3149 - acc: 0.8969 - val_loss: 0.3886 - val_acc: 0.8799\n",
       "Epoch 5/30\n",
-      "3/3 [==============================] - 1s 147ms/step - loss: 0.5758 - acc: 0.8259 - val_loss: 0.9046 - val_acc: 0.6835\n",
+      "112/112 [==============================] - 33s 292ms/step - loss: 0.2916 - acc: 0.9032 - val_loss: 0.3701 - val_acc: 0.8802\n",
       "Epoch 6/30\n",
-      "3/3 [==============================] - 1s 151ms/step - loss: 0.3592 - acc: 0.9114 - val_loss: 0.8051 - val_acc: 0.7089\n",
+      "112/112 [==============================] - 33s 293ms/step - loss: 0.2735 - acc: 0.9118 - val_loss: 0.3271 - val_acc: 0.8992\n",
       "Epoch 7/30\n",
-      "3/3 [==============================] - 1s 146ms/step - loss: 0.2827 - acc: 0.9430 - val_loss: 0.7079 - val_acc: 0.7342\n",
+      "112/112 [==============================] - 33s 292ms/step - loss: 0.2507 - acc: 0.9169 - val_loss: 0.3618 - val_acc: 0.8897\n",
       "Epoch 8/30\n",
-      "3/3 [==============================] - 1s 149ms/step - loss: 0.2392 - acc: 0.9494 - val_loss: 0.6183 - val_acc: 0.7595\n",
+      "112/112 [==============================] - 34s 296ms/step - loss: 0.2326 - acc: 0.9220 - val_loss: 0.3089 - val_acc: 0.9034\n",
       "Epoch 9/30\n",
-      "3/3 [==============================] - 1s 153ms/step - loss: 0.2218 - acc: 0.9557 - val_loss: 0.5485 - val_acc: 0.7848\n",
+      "112/112 [==============================] - 34s 296ms/step - loss: 0.2302 - acc: 0.9229 - val_loss: 0.3106 - val_acc: 0.8989\n",
       "Epoch 10/30\n",
-      "3/3 [==============================] - 1s 146ms/step - loss: 0.2056 - acc: 0.9589 - val_loss: 0.4901 - val_acc: 0.8481\n",
+      "112/112 [==============================] - 34s 299ms/step - loss: 0.2245 - acc: 0.9245 - val_loss: 0.2983 - val_acc: 0.9056\n",
       "Epoch 11/30\n",
-      "3/3 [==============================] - 1s 153ms/step - loss: 0.1493 - acc: 0.9652 - val_loss: 0.4952 - val_acc: 0.8228\n",
+      "112/112 [==============================] - 33s 291ms/step - loss: 0.2203 - acc: 0.9250 - val_loss: 0.2885 - val_acc: 0.9084\n",
       "Epoch 12/30\n",
-      "3/3 [==============================] - 1s 150ms/step - loss: 0.1321 - acc: 0.9842 - val_loss: 0.5236 - val_acc: 0.7975\n",
+      "112/112 [==============================] - 33s 291ms/step - loss: 0.1971 - acc: 0.9315 - val_loss: 0.2875 - val_acc: 0.9053\n",
       "Epoch 13/30\n",
-      "3/3 [==============================] - 1s 150ms/step - loss: 0.1146 - acc: 0.9842 - val_loss: 0.5648 - val_acc: 0.7975\n",
+      "112/112 [==============================] - 33s 292ms/step - loss: 0.1951 - acc: 0.9338 - val_loss: 0.2849 - val_acc: 0.9101\n",
       "Epoch 14/30\n",
-      "3/3 [==============================] - 1s 149ms/step - loss: 0.1094 - acc: 0.9715 - val_loss: 0.6045 - val_acc: 0.7975\n",
+      "112/112 [==============================] - 33s 292ms/step - loss: 0.1906 - acc: 0.9368 - val_loss: 0.2891 - val_acc: 0.9078\n",
       "Epoch 15/30\n",
-      "3/3 [==============================] - 1s 150ms/step - loss: 0.0935 - acc: 0.9810 - val_loss: 0.6233 - val_acc: 0.7848\n",
+      "112/112 [==============================] - 33s 292ms/step - loss: 0.1937 - acc: 0.9338 - val_loss: 0.3313 - val_acc: 0.8953\n",
       "Epoch 16/30\n",
-      "3/3 [==============================] - 1s 145ms/step - loss: 0.0959 - acc: 0.9810 - val_loss: 0.6089 - val_acc: 0.7848\n",
+      "112/112 [==============================] - 33s 291ms/step - loss: 0.1865 - acc: 0.9349 - val_loss: 0.2739 - val_acc: 0.9134\n",
       "Epoch 17/30\n",
-      "3/3 [==============================] - 1s 153ms/step - loss: 0.0788 - acc: 0.9937 - val_loss: 0.5710 - val_acc: 0.7848\n",
+      "112/112 [==============================] - 33s 293ms/step - loss: 0.1842 - acc: 0.9357 - val_loss: 0.3166 - val_acc: 0.8995\n",
       "Epoch 18/30\n",
-      "3/3 [==============================] - 1s 149ms/step - loss: 0.0767 - acc: 0.9937 - val_loss: 0.5456 - val_acc: 0.7975\n",
+      "112/112 [==============================] - 35s 306ms/step - loss: 0.1843 - acc: 0.9374 - val_loss: 0.2798 - val_acc: 0.9078\n",
       "Epoch 19/30\n",
-      "3/3 [==============================] - 1s 148ms/step - loss: 0.0727 - acc: 0.9810 - val_loss: 0.5637 - val_acc: 0.7975\n",
+      "112/112 [==============================] - 34s 297ms/step - loss: 0.1736 - acc: 0.9395 - val_loss: 0.2665 - val_acc: 0.9140\n",
       "Epoch 20/30\n",
-      "3/3 [==============================] - 1s 152ms/step - loss: 0.0801 - acc: 0.9905 - val_loss: 0.5570 - val_acc: 0.7975\n",
+      "112/112 [==============================] - 33s 294ms/step - loss: 0.1759 - acc: 0.9396 - val_loss: 0.2782 - val_acc: 0.9065\n",
       "Epoch 21/30\n",
-      "3/3 [==============================] - 1s 152ms/step - loss: 0.0676 - acc: 0.9842 - val_loss: 0.5506 - val_acc: 0.7975\n",
+      "112/112 [==============================] - 33s 292ms/step - loss: 0.1713 - acc: 0.9423 - val_loss: 0.2938 - val_acc: 0.9073\n",
       "Epoch 22/30\n",
-      "3/3 [==============================] - 1s 144ms/step - loss: 0.0691 - acc: 0.9873 - val_loss: 0.5589 - val_acc: 0.7975\n",
+      "112/112 [==============================] - 33s 292ms/step - loss: 0.1726 - acc: 0.9402 - val_loss: 0.3162 - val_acc: 0.9067\n",
       "Epoch 23/30\n",
-      "3/3 [==============================] - 1s 149ms/step - loss: 0.0911 - acc: 0.9778 - val_loss: 0.5682 - val_acc: 0.7975\n",
+      "112/112 [==============================] - 33s 294ms/step - loss: 0.1714 - acc: 0.9430 - val_loss: 0.2765 - val_acc: 0.9123\n",
       "Epoch 24/30\n",
-      "3/3 [==============================] - 1s 150ms/step - loss: 0.0602 - acc: 0.9873 - val_loss: 0.5239 - val_acc: 0.7975\n",
+      "112/112 [==============================] - 33s 291ms/step - loss: 0.1597 - acc: 0.9452 - val_loss: 0.2709 - val_acc: 0.9143\n",
       "Epoch 25/30\n",
-      "3/3 [==============================] - 1s 149ms/step - loss: 0.0581 - acc: 0.9905 - val_loss: 0.4833 - val_acc: 0.8101\n",
+      "112/112 [==============================] - 33s 294ms/step - loss: 0.1550 - acc: 0.9451 - val_loss: 0.2921 - val_acc: 0.9025\n",
       "Epoch 26/30\n",
-      "3/3 [==============================] - 1s 150ms/step - loss: 0.0525 - acc: 0.9968 - val_loss: 0.4710 - val_acc: 0.8101\n",
+      "112/112 [==============================] - 33s 294ms/step - loss: 0.1589 - acc: 0.9429 - val_loss: 0.2790 - val_acc: 0.9145\n",
       "Epoch 27/30\n",
-      "3/3 [==============================] - 1s 148ms/step - loss: 0.0531 - acc: 0.9937 - val_loss: 0.4709 - val_acc: 0.8101\n",
+      "112/112 [==============================] - 33s 294ms/step - loss: 0.1605 - acc: 0.9449 - val_loss: 0.2705 - val_acc: 0.9162\n",
       "Epoch 28/30\n",
-      "3/3 [==============================] - 1s 146ms/step - loss: 0.0820 - acc: 0.9842 - val_loss: 0.4476 - val_acc: 0.8228\n",
+      "112/112 [==============================] - 33s 293ms/step - loss: 0.1653 - acc: 0.9418 - val_loss: 0.2837 - val_acc: 0.9137\n",
       "Epoch 29/30\n",
-      "3/3 [==============================] - 1s 150ms/step - loss: 0.0373 - acc: 1.0000 - val_loss: 0.4158 - val_acc: 0.8481\n",
+      "112/112 [==============================] - 33s 292ms/step - loss: 0.1657 - acc: 0.9423 - val_loss: 0.3002 - val_acc: 0.9059\n",
       "Epoch 30/30\n",
-      "3/3 [==============================] - 1s 147ms/step - loss: 0.0432 - acc: 0.9968 - val_loss: 0.4003 - val_acc: 0.8608\n"
+      "112/112 [==============================] - 33s 292ms/step - loss: 0.1650 - acc: 0.9437 - val_loss: 0.2658 - val_acc: 0.9165\n"
      ]
     },
     {
      "data": {
       "text/plain": [
-       "<keras.callbacks.History at 0x2087722aa30>"
+       "<keras.callbacks.History at 0x1899825f400>"
       ]
      },
-     "execution_count": 11,
+     "execution_count": 14,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -299,17 +299,24 @@
    "source": [
     "model.fit(train_ds,\n",
     "            validation_data=val_ds,\n",
-    "            epochs=30,)\n",
+    "            epochs=30)\n",
     "            "
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
    "metadata": {},
    "outputs": [],
    "source": [
-    "model.save_weights(weights_path+'/weights')"
+    "model.save_weights(weights_path+'/weights2')"
    ]
   },
   {
@@ -321,7 +328,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 16,
    "metadata": {},
    "outputs": [
     {
@@ -334,10 +341,10 @@
     {
      "data": {
       "text/plain": [
-       "<matplotlib.image.AxesImage at 0x24f9b4d1130>"
+       "<matplotlib.image.AxesImage at 0x18999edd1c0>"
       ]
      },
-     "execution_count": 15,
+     "execution_count": 16,
      "metadata": {},
      "output_type": "execute_result"
     },
@@ -364,7 +371,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 17,
    "metadata": {},
    "outputs": [
     {
@@ -373,7 +380,7 @@
        "'50'"
       ]
      },
-     "execution_count": 16,
+     "execution_count": 17,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -394,9 +401,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 18,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "100\n"
+     ]
+    }
+   ],
    "source": [
     "from IPython.display import clear_output\n",
     "\n",
@@ -424,6 +439,77 @@
     "captura.release()\n",
     "cv2.destroyAllWindows()"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# imgae augmentation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Initialised with 1782 image(s) found.\n",
+      "Output directory set to BilletesMexico/BilletesMexico_img\\output."
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Processing <PIL.Image.Image image mode=RGB size=640x480 at 0x18999F2B910>:  26%|██▌       | 1564/6000 [00:18<00:53, 83.09 Samples/s]                     \n"
+     ]
+    },
+    {
+     "ename": "ValueError",
+     "evalue": "image has wrong mode",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mValueError\u001b[0m                                Traceback (most recent call last)",
+      "\u001b[1;32mc:\\Users\\franz\\Billdetector\\billetes.ipynb Cell 22'\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m     <a href='vscode-notebook-cell:/c%3A/Users/franz/Billdetector/billetes.ipynb#ch0000028?line=12'>13</a>\u001b[0m p\u001b[39m.\u001b[39mrandom_color(\u001b[39m.3\u001b[39m,min_factor\u001b[39m=\u001b[39m\u001b[39m.5\u001b[39m,max_factor\u001b[39m=\u001b[39m\u001b[39m.99\u001b[39m)\n\u001b[0;32m     <a href='vscode-notebook-cell:/c%3A/Users/franz/Billdetector/billetes.ipynb#ch0000028?line=14'>15</a>\u001b[0m \u001b[39m#p.random_erasing(.1,rectangle_area=.2)\u001b[39;00m\n\u001b[0;32m     <a href='vscode-notebook-cell:/c%3A/Users/franz/Billdetector/billetes.ipynb#ch0000028?line=15'>16</a>\u001b[0m \u001b[39m#p.rotate_without_crop(.2,max_left_rotation=10,max_right_rotation=10)\u001b[39;00m\n\u001b[0;32m     <a href='vscode-notebook-cell:/c%3A/Users/franz/Billdetector/billetes.ipynb#ch0000028?line=16'>17</a>\u001b[0m \u001b[39m#p.zoom_random(.2,percentage_area=.5)\u001b[39;00m\n\u001b[1;32m---> <a href='vscode-notebook-cell:/c%3A/Users/franz/Billdetector/billetes.ipynb#ch0000028?line=17'>18</a>\u001b[0m p\u001b[39m.\u001b[39;49msample(\u001b[39m6000\u001b[39;49m)\n",
+      "File \u001b[1;32m~\\.conda\\envs\\tf-gpu\\lib\\site-packages\\Augmentor\\Pipeline.py:364\u001b[0m, in \u001b[0;36mPipeline.sample\u001b[1;34m(self, n, multi_threaded)\u001b[0m\n\u001b[0;32m    <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/Augmentor/Pipeline.py?line=361'>362</a>\u001b[0m \u001b[39mwith\u001b[39;00m tqdm(total\u001b[39m=\u001b[39m\u001b[39mlen\u001b[39m(augmentor_images), desc\u001b[39m=\u001b[39m\u001b[39m\"\u001b[39m\u001b[39mExecuting Pipeline\u001b[39m\u001b[39m\"\u001b[39m, unit\u001b[39m=\u001b[39m\u001b[39m\"\u001b[39m\u001b[39m Samples\u001b[39m\u001b[39m\"\u001b[39m) \u001b[39mas\u001b[39;00m progress_bar:\n\u001b[0;32m    <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/Augmentor/Pipeline.py?line=362'>363</a>\u001b[0m     \u001b[39mwith\u001b[39;00m ThreadPoolExecutor(max_workers\u001b[39m=\u001b[39m\u001b[39mNone\u001b[39;00m) \u001b[39mas\u001b[39;00m executor:\n\u001b[1;32m--> <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/Augmentor/Pipeline.py?line=363'>364</a>\u001b[0m         \u001b[39mfor\u001b[39;00m result \u001b[39min\u001b[39;00m executor\u001b[39m.\u001b[39mmap(\u001b[39mself\u001b[39m, augmentor_images):\n\u001b[0;32m    <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/Augmentor/Pipeline.py?line=364'>365</a>\u001b[0m             progress_bar\u001b[39m.\u001b[39mset_description(\u001b[39m\"\u001b[39m\u001b[39mProcessing \u001b[39m\u001b[39m%s\u001b[39;00m\u001b[39m\"\u001b[39m \u001b[39m%\u001b[39m result)\n\u001b[0;32m    <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/Augmentor/Pipeline.py?line=365'>366</a>\u001b[0m             progress_bar\u001b[39m.\u001b[39mupdate(\u001b[39m1\u001b[39m)\n",
+      "File \u001b[1;32m~\\.conda\\envs\\tf-gpu\\lib\\concurrent\\futures\\_base.py:608\u001b[0m, in \u001b[0;36mExecutor.map.<locals>.result_iterator\u001b[1;34m()\u001b[0m\n\u001b[0;32m    <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/concurrent/futures/_base.py?line=604'>605</a>\u001b[0m \u001b[39mwhile\u001b[39;00m fs:\n\u001b[0;32m    <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/concurrent/futures/_base.py?line=605'>606</a>\u001b[0m     \u001b[39m# Careful not to keep a reference to the popped future\u001b[39;00m\n\u001b[0;32m    <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/concurrent/futures/_base.py?line=606'>607</a>\u001b[0m     \u001b[39mif\u001b[39;00m timeout \u001b[39mis\u001b[39;00m \u001b[39mNone\u001b[39;00m:\n\u001b[1;32m--> <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/concurrent/futures/_base.py?line=607'>608</a>\u001b[0m         \u001b[39myield\u001b[39;00m fs\u001b[39m.\u001b[39;49mpop()\u001b[39m.\u001b[39;49mresult()\n\u001b[0;32m    <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/concurrent/futures/_base.py?line=608'>609</a>\u001b[0m     \u001b[39melse\u001b[39;00m:\n\u001b[0;32m    <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/concurrent/futures/_base.py?line=609'>610</a>\u001b[0m         \u001b[39myield\u001b[39;00m fs\u001b[39m.\u001b[39mpop()\u001b[39m.\u001b[39mresult(end_time \u001b[39m-\u001b[39m time\u001b[39m.\u001b[39mmonotonic())\n",
+      "File \u001b[1;32m~\\.conda\\envs\\tf-gpu\\lib\\concurrent\\futures\\_base.py:438\u001b[0m, in \u001b[0;36mFuture.result\u001b[1;34m(self, timeout)\u001b[0m\n\u001b[0;32m    <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/concurrent/futures/_base.py?line=435'>436</a>\u001b[0m     \u001b[39mraise\u001b[39;00m CancelledError()\n\u001b[0;32m    <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/concurrent/futures/_base.py?line=436'>437</a>\u001b[0m \u001b[39melif\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_state \u001b[39m==\u001b[39m FINISHED:\n\u001b[1;32m--> <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/concurrent/futures/_base.py?line=437'>438</a>\u001b[0m     \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m__get_result()\n\u001b[0;32m    <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/concurrent/futures/_base.py?line=439'>440</a>\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_condition\u001b[39m.\u001b[39mwait(timeout)\n\u001b[0;32m    <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/concurrent/futures/_base.py?line=441'>442</a>\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_state \u001b[39min\u001b[39;00m [CANCELLED, CANCELLED_AND_NOTIFIED]:\n",
+      "File \u001b[1;32m~\\.conda\\envs\\tf-gpu\\lib\\concurrent\\futures\\_base.py:390\u001b[0m, in \u001b[0;36mFuture.__get_result\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m    <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/concurrent/futures/_base.py?line=387'>388</a>\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_exception:\n\u001b[0;32m    <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/concurrent/futures/_base.py?line=388'>389</a>\u001b[0m     \u001b[39mtry\u001b[39;00m:\n\u001b[1;32m--> <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/concurrent/futures/_base.py?line=389'>390</a>\u001b[0m         \u001b[39mraise\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_exception\n\u001b[0;32m    <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/concurrent/futures/_base.py?line=390'>391</a>\u001b[0m     \u001b[39mfinally\u001b[39;00m:\n\u001b[0;32m    <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/concurrent/futures/_base.py?line=391'>392</a>\u001b[0m         \u001b[39m# Break a reference cycle with the exception in self._exception\u001b[39;00m\n\u001b[0;32m    <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/concurrent/futures/_base.py?line=392'>393</a>\u001b[0m         \u001b[39mself\u001b[39m \u001b[39m=\u001b[39m \u001b[39mNone\u001b[39;00m\n",
+      "File \u001b[1;32m~\\.conda\\envs\\tf-gpu\\lib\\concurrent\\futures\\thread.py:52\u001b[0m, in \u001b[0;36m_WorkItem.run\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m     <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/concurrent/futures/thread.py?line=48'>49</a>\u001b[0m     \u001b[39mreturn\u001b[39;00m\n\u001b[0;32m     <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/concurrent/futures/thread.py?line=50'>51</a>\u001b[0m \u001b[39mtry\u001b[39;00m:\n\u001b[1;32m---> <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/concurrent/futures/thread.py?line=51'>52</a>\u001b[0m     result \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mfn(\u001b[39m*\u001b[39m\u001b[39mself\u001b[39m\u001b[39m.\u001b[39margs, \u001b[39m*\u001b[39m\u001b[39m*\u001b[39m\u001b[39mself\u001b[39m\u001b[39m.\u001b[39mkwargs)\n\u001b[0;32m     <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/concurrent/futures/thread.py?line=52'>53</a>\u001b[0m \u001b[39mexcept\u001b[39;00m \u001b[39mBaseException\u001b[39;00m \u001b[39mas\u001b[39;00m exc:\n\u001b[0;32m     <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/concurrent/futures/thread.py?line=53'>54</a>\u001b[0m     \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mfuture\u001b[39m.\u001b[39mset_exception(exc)\n",
+      "File \u001b[1;32m~\\.conda\\envs\\tf-gpu\\lib\\site-packages\\Augmentor\\Pipeline.py:105\u001b[0m, in \u001b[0;36mPipeline.__call__\u001b[1;34m(self, augmentor_image)\u001b[0m\n\u001b[0;32m     <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/Augmentor/Pipeline.py?line=91'>92</a>\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39m__call__\u001b[39m(\u001b[39mself\u001b[39m, augmentor_image):\n\u001b[0;32m     <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/Augmentor/Pipeline.py?line=92'>93</a>\u001b[0m     \u001b[39m\"\"\"\u001b[39;00m\n\u001b[0;32m     <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/Augmentor/Pipeline.py?line=93'>94</a>\u001b[0m \u001b[39m    Function used by the ThreadPoolExecutor to process the pipeline\u001b[39;00m\n\u001b[0;32m     <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/Augmentor/Pipeline.py?line=94'>95</a>\u001b[0m \u001b[39m    using multiple threads. Do not call directly.\u001b[39;00m\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m    <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/Augmentor/Pipeline.py?line=102'>103</a>\u001b[0m \u001b[39m    :return: None\u001b[39;00m\n\u001b[0;32m    <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/Augmentor/Pipeline.py?line=103'>104</a>\u001b[0m \u001b[39m    \"\"\"\u001b[39;00m\n\u001b[1;32m--> <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/Augmentor/Pipeline.py?line=104'>105</a>\u001b[0m     \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_execute(augmentor_image)\n",
+      "File \u001b[1;32m~\\.conda\\envs\\tf-gpu\\lib\\site-packages\\Augmentor\\Pipeline.py:233\u001b[0m, in \u001b[0;36mPipeline._execute\u001b[1;34m(self, augmentor_image, save_to_disk, multi_threaded)\u001b[0m\n\u001b[0;32m    <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/Augmentor/Pipeline.py?line=230'>231</a>\u001b[0m     r \u001b[39m=\u001b[39m \u001b[39mround\u001b[39m(random\u001b[39m.\u001b[39muniform(\u001b[39m0\u001b[39m, \u001b[39m1\u001b[39m), \u001b[39m1\u001b[39m)\n\u001b[0;32m    <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/Augmentor/Pipeline.py?line=231'>232</a>\u001b[0m     \u001b[39mif\u001b[39;00m r \u001b[39m<\u001b[39m\u001b[39m=\u001b[39m operation\u001b[39m.\u001b[39mprobability:\n\u001b[1;32m--> <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/Augmentor/Pipeline.py?line=232'>233</a>\u001b[0m         images \u001b[39m=\u001b[39m operation\u001b[39m.\u001b[39;49mperform_operation(images)\n\u001b[0;32m    <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/Augmentor/Pipeline.py?line=234'>235</a>\u001b[0m \u001b[39m# TEMP FOR TESTING\u001b[39;00m\n\u001b[0;32m    <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/Augmentor/Pipeline.py?line=235'>236</a>\u001b[0m \u001b[39m# save_to_disk = False\u001b[39;00m\n\u001b[0;32m    <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/Augmentor/Pipeline.py?line=237'>238</a>\u001b[0m \u001b[39mif\u001b[39;00m save_to_disk:\n",
+      "File \u001b[1;32m~\\.conda\\envs\\tf-gpu\\lib\\site-packages\\Augmentor\\Operations.py:417\u001b[0m, in \u001b[0;36mRandomContrast.perform_operation\u001b[1;34m(self, images)\u001b[0m\n\u001b[0;32m    <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/Augmentor/Operations.py?line=413'>414</a>\u001b[0m augmented_images \u001b[39m=\u001b[39m []\n\u001b[0;32m    <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/Augmentor/Operations.py?line=415'>416</a>\u001b[0m \u001b[39mfor\u001b[39;00m image \u001b[39min\u001b[39;00m images:\n\u001b[1;32m--> <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/Augmentor/Operations.py?line=416'>417</a>\u001b[0m     augmented_images\u001b[39m.\u001b[39mappend(do(image))\n\u001b[0;32m    <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/Augmentor/Operations.py?line=418'>419</a>\u001b[0m \u001b[39mreturn\u001b[39;00m augmented_images\n",
+      "File \u001b[1;32m~\\.conda\\envs\\tf-gpu\\lib\\site-packages\\Augmentor\\Operations.py:412\u001b[0m, in \u001b[0;36mRandomContrast.perform_operation.<locals>.do\u001b[1;34m(image)\u001b[0m\n\u001b[0;32m    <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/Augmentor/Operations.py?line=408'>409</a>\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39mdo\u001b[39m(image):\n\u001b[0;32m    <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/Augmentor/Operations.py?line=410'>411</a>\u001b[0m     image_enhancer_contrast \u001b[39m=\u001b[39m ImageEnhance\u001b[39m.\u001b[39mContrast(image)\n\u001b[1;32m--> <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/Augmentor/Operations.py?line=411'>412</a>\u001b[0m     \u001b[39mreturn\u001b[39;00m image_enhancer_contrast\u001b[39m.\u001b[39;49menhance(factor)\n",
+      "File \u001b[1;32m~\\.conda\\envs\\tf-gpu\\lib\\site-packages\\PIL\\ImageEnhance.py:36\u001b[0m, in \u001b[0;36m_Enhance.enhance\u001b[1;34m(self, factor)\u001b[0m\n\u001b[0;32m     <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/PIL/ImageEnhance.py?line=24'>25</a>\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39menhance\u001b[39m(\u001b[39mself\u001b[39m, factor):\n\u001b[0;32m     <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/PIL/ImageEnhance.py?line=25'>26</a>\u001b[0m     \u001b[39m\"\"\"\u001b[39;00m\n\u001b[0;32m     <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/PIL/ImageEnhance.py?line=26'>27</a>\u001b[0m \u001b[39m    Returns an enhanced image.\u001b[39;00m\n\u001b[0;32m     <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/PIL/ImageEnhance.py?line=27'>28</a>\u001b[0m \n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m     <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/PIL/ImageEnhance.py?line=33'>34</a>\u001b[0m \u001b[39m    :rtype: :py:class:`~PIL.Image.Image`\u001b[39;00m\n\u001b[0;32m     <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/PIL/ImageEnhance.py?line=34'>35</a>\u001b[0m \u001b[39m    \"\"\"\u001b[39;00m\n\u001b[1;32m---> <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/PIL/ImageEnhance.py?line=35'>36</a>\u001b[0m     \u001b[39mreturn\u001b[39;00m Image\u001b[39m.\u001b[39;49mblend(\u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mdegenerate, \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mimage, factor)\n",
+      "File \u001b[1;32m~\\.conda\\envs\\tf-gpu\\lib\\site-packages\\PIL\\Image.py:3052\u001b[0m, in \u001b[0;36mblend\u001b[1;34m(im1, im2, alpha)\u001b[0m\n\u001b[0;32m   <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/PIL/Image.py?line=3049'>3050</a>\u001b[0m im1\u001b[39m.\u001b[39mload()\n\u001b[0;32m   <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/PIL/Image.py?line=3050'>3051</a>\u001b[0m im2\u001b[39m.\u001b[39mload()\n\u001b[1;32m-> <a href='file:///c%3A/Users/franz/.conda/envs/tf-gpu/lib/site-packages/PIL/Image.py?line=3051'>3052</a>\u001b[0m \u001b[39mreturn\u001b[39;00m im1\u001b[39m.\u001b[39m_new(core\u001b[39m.\u001b[39;49mblend(im1\u001b[39m.\u001b[39;49mim, im2\u001b[39m.\u001b[39;49mim, alpha))\n",
+      "\u001b[1;31mValueError\u001b[0m: image has wrong mode"
+     ]
+    }
+   ],
+   "source": [
+    "import Augmentor\n",
+    "# Passing the path of the image directory\n",
+    "p = Augmentor.Pipeline(data_path)\n",
+    "  \n",
+    "# Defining augmentation parameters and generating 5 samples\n",
+    "p.flip_left_right(0.5)\n",
+    "#p.black_and_white(0.1)\n",
+    "p.rotate(0.3, 10, 10)\n",
+    "p.skew(0.4, 0.5)\n",
+    "p.zoom(probability = 0.2, min_factor = .5, max_factor = 1.5)\n",
+    "\n",
+    "p.random_contrast(0.2,min_factor=0.3,max_factor=.9)\n",
+    "p.random_color(.3,min_factor=.5,max_factor=.99)\n",
+    "\n",
+    "#p.random_erasing(.1,rectangle_area=.2)\n",
+    "#p.rotate_without_crop(.2,max_left_rotation=10,max_right_rotation=10)\n",
+    "#p.zoom_random(.2,percentage_area=.5)\n",
+    "p.sample(6000)"
+   ]
   }
  ],
  "metadata": {