working code

notes/mnist.ipynb

@@ -6,18 +6,18 @@
    "id": "b2d6f096-6123-4dd0-ae4f-c9abf70889c4",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-04-04T08:47:31.680497Z",
-     "iopub.status.busy": "2024-04-04T08:47:31.678982Z",
-     "iopub.status.idle": "2024-04-04T08:47:52.012034Z",
-     "shell.execute_reply": "2024-04-04T08:47:52.010508Z",
-     "shell.execute_reply.started": "2024-04-04T08:47:31.680435Z"
+     "iopub.execute_input": "2024-04-04T11:32:11.084868Z",
+     "iopub.status.busy": "2024-04-04T11:32:11.084300Z",
+     "iopub.status.idle": "2024-04-04T11:32:37.677559Z",
+     "shell.execute_reply": "2024-04-04T11:32:37.674899Z",
+     "shell.execute_reply.started": "2024-04-04T11:32:11.084821Z"
     }
    },
    "outputs": [
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "f0c8978e9991468cb37176b7ee5e7f40",
+       "model_id": "89f99ed2104c400c89a0a4079cc36f94",
        "version_major": 2,
        "version_minor": 0
       },
@@ -31,7 +31,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "1821c061525d4be1b088a0b1624ba0f7",
+       "model_id": "b925c2c62913473aa1a8047fb2003609",
        "version_major": 2,
        "version_minor": 0
       },
@@ -52,7 +52,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "eb3da6f2299d4012862a28dd3a74565d",
+       "model_id": "62bc67afecc2488d84e6dc0d59fb3f1f",
        "version_major": 2,
        "version_minor": 0
       },
@@ -66,7 +66,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "e53657e2c6ad4c108ad703dae1f87efe",
+       "model_id": "2a2f6c3e41574694948f051a0fe10c3d",
        "version_major": 2,
        "version_minor": 0
       },
@@ -80,7 +80,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "2407ea55dc5348619ad666a16a3b97ff",
+       "model_id": "7e7d94cbfe3147ff80323ebe74b0e960",
        "version_major": 2,
        "version_minor": 0
       },
@@ -94,7 +94,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "04a14bdbb03044979afd7c44ba0f424e",
+       "model_id": "67f4f2d45c354e7da9114a7638fd2098",
        "version_major": 2,
        "version_minor": 0
       },
@@ -108,7 +108,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "976dba4172974f01ae37ad90b1c6cb1d",
+       "model_id": "c3ed5a8fe6c64817933a0cd892152949",
        "version_major": 2,
        "version_minor": 0
       },
@@ -122,7 +122,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "56d60d708f2549a5a0c6acc0e2499884",
+       "model_id": "347a6af016c54c5098f4544fe8666d2c",
        "version_major": 2,
        "version_minor": 0
       },
@@ -136,7 +136,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "87ba67ec7d834407afd7fcf7a9d6ac13",
+       "model_id": "a5d6a4133e5f4b2f99fb819bb879db0f",
        "version_major": 2,
        "version_minor": 0
       },
@@ -150,7 +150,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "696c5019b4c24f049ce78744c1fecded",
+       "model_id": "7a4468bfba904b6bad4575a5b73a2be1",
        "version_major": 2,
        "version_minor": 0
       },
@@ -171,7 +171,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "d5193a728c974100b02fcb82ac236d80",
+       "model_id": "a9065c53e61d4dc7b258f008eb91d136",
        "version_major": 2,
        "version_minor": 0
       },
@@ -192,14 +192,14 @@
   {
    "cell_type": "code",
    "execution_count": 2,
-   "id": "7c5ea43d-6a70-4deb-a90e-1d7758c961a3",
+   "id": "ddf255fe-a5dc-47b7-acf8-9bb1c636679f",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-04-04T08:47:52.015528Z",
-     "iopub.status.busy": "2024-04-04T08:47:52.014998Z",
-     "iopub.status.idle": "2024-04-04T08:47:56.923333Z",
-     "shell.execute_reply": "2024-04-04T08:47:56.922341Z",
-     "shell.execute_reply.started": "2024-04-04T08:47:52.015483Z"
+     "iopub.execute_input": "2024-04-04T11:32:37.680763Z",
+     "iopub.status.busy": "2024-04-04T11:32:37.680286Z",
+     "iopub.status.idle": "2024-04-04T11:32:53.674997Z",
+     "shell.execute_reply": "2024-04-04T11:32:53.673895Z",
+     "shell.execute_reply.started": "2024-04-04T11:32:37.680723Z"
     }
    },
    "outputs": [],
@@ -209,55 +209,28 @@
     "import io\n",
     "import tensorflow as tf\n",
     "\n",
-    "def convert_image(byte_like_str_image):\n",
-    "    return tf.convert_to_tensor(np.asarray(Image.open(io.BytesIO(byte_like_str_image['bytes']))), dtype = tf.float32)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "daafde17-8100-4f49-b27e-8aad43b129c6",
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2024-04-04T08:47:56.925474Z",
-     "iopub.status.busy": "2024-04-04T08:47:56.924961Z",
-     "iopub.status.idle": "2024-04-04T08:48:32.236745Z",
-     "shell.execute_reply": "2024-04-04T08:48:32.234178Z",
-     "shell.execute_reply.started": "2024-04-04T08:47:56.925446Z"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "from keras.utils import to_categorical\n",
-    "\n",
-    "dataset_train = dataset['train'].to_pandas()\n",
-    "dataset_train['image'] = dataset_train['image'].map(convert_image)\n",
+    "dataset_train = dataset['train']\n",
+    "dataset_test = dataset['test']\n",
     "\n",
-    "dataset_test = dataset['test'].to_pandas()\n",
-    "dataset_test['image'] = dataset_test['image'].map(convert_image)\n",
+    "X_train = np.array([np.array(PIL_object) for PIL_object in dataset_train['image']], dtype='float32')\n",
+    "X_test = np.array([np.array(PIL_object) for PIL_object in dataset_test['image']], dtype='float32')\n",
     "\n",
-    "# Convert labels to NumPy arrays\n",
-    "X_train = np.array(dataset_train['image'].tolist())\n",
     "y_train = np.array(dataset_train['label'])\n",
-    "\n",
-    "X_test = np.array(dataset_test['image'].tolist())\n",
     "y_test = np.array(dataset_test['label'])\n",
-    "# dataset_train['label'] = dataset_train['label'].astype('float32')\n",
-    "# dataset_test['label'] = dataset_test['label'].astype('float32')\n",
-    "\n"
+    "    \n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 3,
    "id": "72022fd2-000d-4d5c-88d5-9afc62c283d5",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-04-04T08:48:32.239111Z",
-     "iopub.status.busy": "2024-04-04T08:48:32.238769Z",
-     "iopub.status.idle": "2024-04-04T08:48:32.369358Z",
-     "shell.execute_reply": "2024-04-04T08:48:32.367989Z",
-     "shell.execute_reply.started": "2024-04-04T08:48:32.239071Z"
+     "iopub.execute_input": "2024-04-04T11:32:53.682038Z",
+     "iopub.status.busy": "2024-04-04T11:32:53.681712Z",
+     "iopub.status.idle": "2024-04-04T11:32:55.198308Z",
+     "shell.execute_reply": "2024-04-04T11:32:55.196384Z",
+     "shell.execute_reply.started": "2024-04-04T11:32:53.682010Z"
     }
    },
    "outputs": [],
@@ -273,15 +246,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 4,
    "id": "dd7871ac-cacd-4866-bdda-67651f592262",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-04-04T08:48:32.371520Z",
-     "iopub.status.busy": "2024-04-04T08:48:32.371132Z",
-     "iopub.status.idle": "2024-04-04T08:48:32.391109Z",
-     "shell.execute_reply": "2024-04-04T08:48:32.390162Z",
-     "shell.execute_reply.started": "2024-04-04T08:48:32.371484Z"
+     "iopub.execute_input": "2024-04-04T11:32:55.224011Z",
+     "iopub.status.busy": "2024-04-04T11:32:55.223548Z",
+     "iopub.status.idle": "2024-04-04T11:32:55.254034Z",
+     "shell.execute_reply": "2024-04-04T11:32:55.252607Z",
+     "shell.execute_reply.started": "2024-04-04T11:32:55.223968Z"
     }
    },
    "outputs": [],
@@ -295,15 +268,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 5,
    "id": "280e0d9d-d9e8-41d9-b9ad-666e84fc0bfa",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-04-04T08:48:32.392690Z",
-     "iopub.status.busy": "2024-04-04T08:48:32.392405Z",
-     "iopub.status.idle": "2024-04-04T08:49:02.402966Z",
-     "shell.execute_reply": "2024-04-04T08:49:02.402204Z",
-     "shell.execute_reply.started": "2024-04-04T08:48:32.392662Z"
+     "iopub.execute_input": "2024-04-04T11:32:55.260216Z",
+     "iopub.status.busy": "2024-04-04T11:32:55.259580Z",
+     "iopub.status.idle": "2024-04-04T11:34:50.315214Z",
+     "shell.execute_reply": "2024-04-04T11:34:50.310372Z",
+     "shell.execute_reply.started": "2024-04-04T11:32:55.260155Z"
     }
    },
    "outputs": [
@@ -311,52 +284,55 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Epoch 1/5\n",
-      "1875/1875 [==============================] - 7s 3ms/step - loss: 2.6159 - sparse_categorical_accuracy: 0.8597 - val_loss: 0.5951 - val_sparse_categorical_accuracy: 0.8762\n",
-      "Epoch 2/5\n",
-      "1875/1875 [==============================] - 6s 3ms/step - loss: 0.4041 - sparse_categorical_accuracy: 0.9071 - val_loss: 0.4567 - val_sparse_categorical_accuracy: 0.9024\n",
-      "Epoch 3/5\n",
-      "1875/1875 [==============================] - 6s 3ms/step - loss: 0.2977 - sparse_categorical_accuracy: 0.9247 - val_loss: 0.3300 - val_sparse_categorical_accuracy: 0.9237\n",
-      "Epoch 4/5\n",
-      "1875/1875 [==============================] - 5s 3ms/step - loss: 0.2646 - sparse_categorical_accuracy: 0.9344 - val_loss: 0.2909 - val_sparse_categorical_accuracy: 0.9368\n",
-      "Epoch 5/5\n",
-      "1875/1875 [==============================] - 5s 3ms/step - loss: 0.2418 - sparse_categorical_accuracy: 0.9391 - val_loss: 0.2886 - val_sparse_categorical_accuracy: 0.9330\n",
-      "<class 'pandas.core.frame.DataFrame'>\n",
-      "RangeIndex: 60000 entries, 0 to 59999\n",
-      "Data columns (total 2 columns):\n",
-      " #   Column  Non-Null Count  Dtype \n",
-      "---  ------  --------------  ----- \n",
-      " 0   image   60000 non-null  object\n",
-      " 1   label   60000 non-null  int64 \n",
-      "dtypes: int64(1), object(1)\n",
-      "memory usage: 937.6+ KB\n"
+      "Epoch 1/10\n",
+      "1875/1875 [==============================] - 14s 6ms/step - loss: 2.5253 - sparse_categorical_accuracy: 0.8622 - val_loss: 0.4438 - val_sparse_categorical_accuracy: 0.8893\n",
+      "Epoch 2/10\n",
+      "1875/1875 [==============================] - 11s 6ms/step - loss: 0.3722 - sparse_categorical_accuracy: 0.9146 - val_loss: 0.3441 - val_sparse_categorical_accuracy: 0.9107\n",
+      "Epoch 3/10\n",
+      "1875/1875 [==============================] - 10s 5ms/step - loss: 0.2708 - sparse_categorical_accuracy: 0.9325 - val_loss: 0.2953 - val_sparse_categorical_accuracy: 0.9309\n",
+      "Epoch 4/10\n",
+      "1875/1875 [==============================] - 10s 6ms/step - loss: 0.2511 - sparse_categorical_accuracy: 0.9359 - val_loss: 0.2580 - val_sparse_categorical_accuracy: 0.9378\n",
+      "Epoch 5/10\n",
+      "1875/1875 [==============================] - 11s 6ms/step - loss: 0.2224 - sparse_categorical_accuracy: 0.9435 - val_loss: 0.2646 - val_sparse_categorical_accuracy: 0.9400\n",
+      "Epoch 6/10\n",
+      "1875/1875 [==============================] - 11s 6ms/step - loss: 0.2134 - sparse_categorical_accuracy: 0.9463 - val_loss: 0.2550 - val_sparse_categorical_accuracy: 0.9456\n",
+      "Epoch 7/10\n",
+      "1875/1875 [==============================] - 11s 6ms/step - loss: 0.1993 - sparse_categorical_accuracy: 0.9509 - val_loss: 0.2359 - val_sparse_categorical_accuracy: 0.9508\n",
+      "Epoch 8/10\n",
+      "1875/1875 [==============================] - 12s 6ms/step - loss: 0.1871 - sparse_categorical_accuracy: 0.9545 - val_loss: 0.2501 - val_sparse_categorical_accuracy: 0.9499\n",
+      "Epoch 9/10\n",
+      "1875/1875 [==============================] - 13s 7ms/step - loss: 0.1875 - sparse_categorical_accuracy: 0.9549 - val_loss: 0.2230 - val_sparse_categorical_accuracy: 0.9496\n",
+      "Epoch 10/10\n",
+      "1875/1875 [==============================] - 11s 6ms/step - loss: 0.1766 - sparse_categorical_accuracy: 0.9570 - val_loss: 0.2856 - val_sparse_categorical_accuracy: 0.9465\n"
      ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<keras.callbacks.History at 0x7fd5e51fc5e0>"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
     }
    ],
    "source": [
-    "# model.fit(\n",
-    "#     dataset_train['image'], dataset_test['label'],\n",
-    "#     epochs=10,\n",
-    "#     validation_data=(dataset_test['image'], dataset_test['label']),\n",
-    "# )\n",
-    "# dataset_train['label'].head(50)\n",
-    "model.fit(X_train, y_train, epochs=5, validation_data=(X_test, y_test))\n",
-    "\n",
-    "dataset_train.info()\n",
+    "model.fit(X_train, y_train, epochs=10, validation_data=(X_test, y_test))\n",
     "\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 6,
    "id": "c7317f9a-14f4-4908-9895-8bc085900e28",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-04-04T08:49:35.659063Z",
-     "iopub.status.busy": "2024-04-04T08:49:35.658449Z",
-     "iopub.status.idle": "2024-04-04T08:49:36.588926Z",
-     "shell.execute_reply": "2024-04-04T08:49:36.588088Z",
-     "shell.execute_reply.started": "2024-04-04T08:49:35.659019Z"
+     "iopub.execute_input": "2024-04-04T11:34:50.323252Z",
+     "iopub.status.busy": "2024-04-04T11:34:50.322859Z",
+     "iopub.status.idle": "2024-04-04T11:34:51.995390Z",
+     "shell.execute_reply": "2024-04-04T11:34:51.994131Z",
+     "shell.execute_reply.started": "2024-04-04T11:34:50.323222Z"
     }
    },
    "outputs": [
@@ -364,16 +340,16 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "313/313 [==============================] - 1s 3ms/step - loss: 0.2886 - sparse_categorical_accuracy: 0.9330\n"
+      "313/313 [==============================] - 2s 5ms/step - loss: 0.2856 - sparse_categorical_accuracy: 0.9465\n"
      ]
     },
     {
      "data": {
       "text/plain": [
-       "0.9330000281333923"
+       "0.9465000033378601"
       ]
      },
-     "execution_count": 8,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -382,6 +358,197 @@
     "loss, accuracy = model.evaluate(X_test, y_test)\n",
     "accuracy"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "4aaf2641-a8e4-450b-b5c9-230c18211377",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2024-04-04T11:34:52.005924Z",
+     "iopub.status.busy": "2024-04-04T11:34:52.004025Z",
+     "iopub.status.idle": "2024-04-04T11:34:52.106193Z",
+     "shell.execute_reply": "2024-04-04T11:34:52.104405Z",
+     "shell.execute_reply.started": "2024-04-04T11:34:52.005782Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "model.save(\"../models/mnist-digit-classification.keras\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "3a9debbe-0995-403c-8667-947824f0735e",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2024-04-04T11:40:29.415780Z",
+     "iopub.status.busy": "2024-04-04T11:40:29.415049Z",
+     "iopub.status.idle": "2024-04-04T11:40:32.417113Z",
+     "shell.execute_reply": "2024-04-04T11:40:32.415279Z",
+     "shell.execute_reply.started": "2024-04-04T11:40:29.415741Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "1/1 [==============================] - 0s 33ms/step\n",
+      "[[ -1.8562375  41.656296   46.951298   45.414635   20.483383   27.385012\n",
+      "  -48.246223   58.661873   26.281921   26.166122 ]]\n",
+      "1/1 [==============================] - 0s 38ms/step\n",
+      "[[ -1.8562375  41.656296   46.951298   45.414635   20.483383   27.385012\n",
+      "  -48.246223   58.661873   26.281921   26.166122 ]]\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAABwAAAAcCAAAAABXZoBIAAAAxUlEQVR4nGNgGDaAEUKFpD77sfTFHeyS9xQYGBg+X4UKPuk6w8DAwMDAAuGm6l/TMnSweCzLwPDntSTDozPIOhkYGBgYBA3PmDIw/Lh1XShnGi5nBP+9KIRLTuzl/2AokwlDMlv0/U1cGq1//rPDJcfQ+m83Ky45zrM/rHBqrPu3Daec9+8PlrjkhO/+W4ZLjvn0v9vKuCTV/v3zxSUn/+BfMSMuydZ//0xwydl+QpdEClsbHoa7X1AkWZA5F53f4TIWEwAAaRE8kJuHrgAAAAAASUVORK5CYII=\n",
+      "text/plain": [
+       "<PIL.PngImagePlugin.PngImageFile image mode=L size=28x28>"
+      ]
+     },
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "index = 0\n",
+    "IMAGE_HEIGHT = 28\n",
+    "IMAGE_WIDTH = 28\n",
+    "IMAGE_CHANNEL = 1\n",
+    "\n",
+    "# image_to_predict = np.reshape(X_test[0], (1, 28, 28, 1))\n",
+    "image_to_predict = np.reshape(np.array(dataset_test['image'][index]), (1, IMAGE_HEIGHT, IMAGE_WIDTH, IMAGE_CHANNEL))\n",
+    "print(model.predict(image_to_predict))\n",
+    "\n",
+    "\n",
+    "image_to_predict = np.reshape(X_test[index], (1, 28, 28, 1))\n",
+    "print(model.predict(image_to_predict))\n",
+    "\n",
+    "dataset_test['image'][index]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "7e213156-9fe7-422a-bbf1-05ba92584d0a",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2024-04-04T11:36:15.067062Z",
+     "iopub.status.busy": "2024-04-04T11:36:15.066433Z",
+     "iopub.status.idle": "2024-04-04T11:36:16.695706Z",
+     "shell.execute_reply": "2024-04-04T11:36:16.693747Z",
+     "shell.execute_reply.started": "2024-04-04T11:36:15.067008Z"
+    }
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([[  0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,\n",
+       "          0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,\n",
+       "          0,   0],\n",
+       "       [  0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,\n",
+       "          0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,\n",
+       "          0,   0],\n",
+       "       [  0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,\n",
+       "          0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,\n",
+       "          0,   0],\n",
+       "       [  0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,\n",
+       "          0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,\n",
+       "          0,   0],\n",
+       "       [  0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,\n",
+       "          0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,\n",
+       "          0,   0],\n",
+       "       [  0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,\n",
+       "          0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,\n",
+       "          0,   0],\n",
+       "       [  0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,\n",
+       "          0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,\n",
+       "          0,   0],\n",
+       "       [  0,   0,   0,   0,   0,   0,  84, 185, 159, 151,  60,  36,   0,\n",
+       "          0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,\n",
+       "          0,   0],\n",
+       "       [  0,   0,   0,   0,   0,   0, 222, 254, 254, 254, 254, 241, 198,\n",
+       "        198, 198, 198, 198, 198, 198, 198, 170,  52,   0,   0,   0,   0,\n",
+       "          0,   0],\n",
+       "       [  0,   0,   0,   0,   0,   0,  67, 114,  72, 114, 163, 227, 254,\n",
+       "        225, 254, 254, 254, 250, 229, 254, 254, 140,   0,   0,   0,   0,\n",
+       "          0,   0],\n",
+       "       [  0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,  17,  66,\n",
+       "         14,  67,  67,  67,  59,  21, 236, 254, 106,   0,   0,   0,   0,\n",
+       "          0,   0],\n",
+       "       [  0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,\n",
+       "          0,   0,   0,   0,   0,  83, 253, 209,  18,   0,   0,   0,   0,\n",
+       "          0,   0],\n",
+       "       [  0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,\n",
+       "          0,   0,   0,   0,  22, 233, 255,  83,   0,   0,   0,   0,   0,\n",
+       "          0,   0],\n",
+       "       [  0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,\n",
+       "          0,   0,   0,   0, 129, 254, 238,  44,   0,   0,   0,   0,   0,\n",
+       "          0,   0],\n",
+       "       [  0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,\n",
+       "          0,   0,   0,  59, 249, 254,  62,   0,   0,   0,   0,   0,   0,\n",
+       "          0,   0],\n",
+       "       [  0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,\n",
+       "          0,   0,   0, 133, 254, 187,   5,   0,   0,   0,   0,   0,   0,\n",
+       "          0,   0],\n",
+       "       [  0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,\n",
+       "          0,   0,   9, 205, 248,  58,   0,   0,   0,   0,   0,   0,   0,\n",
+       "          0,   0],\n",
+       "       [  0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,\n",
+       "          0,   0, 126, 254, 182,   0,   0,   0,   0,   0,   0,   0,   0,\n",
+       "          0,   0],\n",
+       "       [  0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,\n",
+       "          0,  75, 251, 240,  57,   0,   0,   0,   0,   0,   0,   0,   0,\n",
+       "          0,   0],\n",
+       "       [  0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,\n",
+       "         19, 221, 254, 166,   0,   0,   0,   0,   0,   0,   0,   0,   0,\n",
+       "          0,   0],\n",
+       "       [  0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   3,\n",
+       "        203, 254, 219,  35,   0,   0,   0,   0,   0,   0,   0,   0,   0,\n",
+       "          0,   0],\n",
+       "       [  0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,  38,\n",
+       "        254, 254,  77,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,\n",
+       "          0,   0],\n",
+       "       [  0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,  31, 224,\n",
+       "        254, 115,   1,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,\n",
+       "          0,   0],\n",
+       "       [  0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0, 133, 254,\n",
+       "        254,  52,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,\n",
+       "          0,   0],\n",
+       "       [  0,   0,   0,   0,   0,   0,   0,   0,   0,   0,  61, 242, 254,\n",
+       "        254,  52,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,\n",
+       "          0,   0],\n",
+       "       [  0,   0,   0,   0,   0,   0,   0,   0,   0,   0, 121, 254, 254,\n",
+       "        219,  40,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,\n",
+       "          0,   0],\n",
+       "       [  0,   0,   0,   0,   0,   0,   0,   0,   0,   0, 121, 254, 207,\n",
+       "         18,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,\n",
+       "          0,   0],\n",
+       "       [  0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,\n",
+       "          0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,   0,\n",
+       "          0,   0]], dtype=uint8)"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a9acdfed-d868-441f-8123-8002d265b95f",
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {