{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"accelerator": "GPU",
"colab": {
"name": "Session_6(L1_and_L2)_3.ipynb",
"provenance": [],
"collapsed_sections": []
},
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.4"
},
"widgets": {
"application/vnd.jupyter.widget-state+json": {
"9cd8896b7dd34a87a99eee8fe6b9696f": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HBoxModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "HBoxModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "HBoxView",
"box_style": "",
"children": [
"IPY_MODEL_1c73b0d38f75415abb42719ddd575514",
"IPY_MODEL_e7823cf07812486489aae4b9acd60037"
],
"layout": "IPY_MODEL_15767740c5f244d4b5cee67c0805e845"
}
},
"15767740c5f244d4b5cee67c0805e845": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"1c73b0d38f75415abb42719ddd575514": {
"model_module": "@jupyter-widgets/controls",
"model_name": "IntProgressModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "IntProgressModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "ProgressView",
"bar_style": "success",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_250fce83a7ea471fa4980abab7410f37",
"max": 1,
"min": 0,
"orientation": "horizontal",
"style": "IPY_MODEL_d7f205d9c7534b168a7d34c1db553e99",
"value": 1
}
},
"e7823cf07812486489aae4b9acd60037": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "HTMLView",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_0ffc1d10d3824646a71697a6ad19e77e",
"placeholder": "",
"style": "IPY_MODEL_c3d463df14a94069a8ecf252ab1fbcb4",
"value": "9920512it [00:06, 1606764.02it/s]"
}
},
"d7f205d9c7534b168a7d34c1db553e99": {
"model_module": "@jupyter-widgets/controls",
"model_name": "ProgressStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "ProgressStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"bar_color": null,
"description_width": ""
}
},
"250fce83a7ea471fa4980abab7410f37": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"c3d463df14a94069a8ecf252ab1fbcb4": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "DescriptionStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"description_width": ""
}
},
"0ffc1d10d3824646a71697a6ad19e77e": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"ded66cf881e04769992669ef97e81de8": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HBoxModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "HBoxModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "HBoxView",
"box_style": "",
"children": [
"IPY_MODEL_6370d4c3e29f464d9369a4e1584895b0",
"IPY_MODEL_afc6bffb76dd412abcc4bfbc27c95943"
],
"layout": "IPY_MODEL_4b3491b1fd644a2b94320f16371f9db2"
}
},
"4b3491b1fd644a2b94320f16371f9db2": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"6370d4c3e29f464d9369a4e1584895b0": {
"model_module": "@jupyter-widgets/controls",
"model_name": "IntProgressModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "IntProgressModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "ProgressView",
"bar_style": "success",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_821ac6d3f2ac4b78ac309f3fc92918b6",
"max": 1,
"min": 0,
"orientation": "horizontal",
"style": "IPY_MODEL_39d55bc2e77a42d6a0e7429422532c10",
"value": 1
}
},
"afc6bffb76dd412abcc4bfbc27c95943": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "HTMLView",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_288756d3fc9844acb6fd36107b1b2b41",
"placeholder": "",
"style": "IPY_MODEL_c01169a89af1436ba347abe350e726a5",
"value": "32768it [00:00, 115638.74it/s]"
}
},
"39d55bc2e77a42d6a0e7429422532c10": {
"model_module": "@jupyter-widgets/controls",
"model_name": "ProgressStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "ProgressStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"bar_color": null,
"description_width": ""
}
},
"821ac6d3f2ac4b78ac309f3fc92918b6": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"c01169a89af1436ba347abe350e726a5": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "DescriptionStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"description_width": ""
}
},
"288756d3fc9844acb6fd36107b1b2b41": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"195384495f93466fac89c8f911014da5": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HBoxModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "HBoxModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "HBoxView",
"box_style": "",
"children": [
"IPY_MODEL_3e72d9d211da4f878e4977e7b6413d11",
"IPY_MODEL_8b848ba7765d49e6bb915248c3923424"
],
"layout": "IPY_MODEL_ea6a26003ef248f4bd94d7622222d5b3"
}
},
"ea6a26003ef248f4bd94d7622222d5b3": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"3e72d9d211da4f878e4977e7b6413d11": {
"model_module": "@jupyter-widgets/controls",
"model_name": "IntProgressModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "IntProgressModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "ProgressView",
"bar_style": "success",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_8941f3c480614fd582c59ab57bf469fc",
"max": 1,
"min": 0,
"orientation": "horizontal",
"style": "IPY_MODEL_68765c521fd646aabc6bfee66c82cc37",
"value": 1
}
},
"8b848ba7765d49e6bb915248c3923424": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "HTMLView",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_b5f1f660daf94c8286931e8c52c09c9b",
"placeholder": "",
"style": "IPY_MODEL_683a1732e1fa45c78bde39c3e1ac29d1",
"value": "1654784it [00:00, 2075696.78it/s]"
}
},
"68765c521fd646aabc6bfee66c82cc37": {
"model_module": "@jupyter-widgets/controls",
"model_name": "ProgressStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "ProgressStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"bar_color": null,
"description_width": ""
}
},
"8941f3c480614fd582c59ab57bf469fc": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"683a1732e1fa45c78bde39c3e1ac29d1": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "DescriptionStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"description_width": ""
}
},
"b5f1f660daf94c8286931e8c52c09c9b": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"3fb3f03ac0154699916e8706210fb08f": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HBoxModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "HBoxModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "HBoxView",
"box_style": "",
"children": [
"IPY_MODEL_a64f617952e04410b8c6275cf6eb4e28",
"IPY_MODEL_0922ce837deb4f208e1f28e25492b7c8"
],
"layout": "IPY_MODEL_e5862969092c48f2a9a77f1f05bf2e65"
}
},
"e5862969092c48f2a9a77f1f05bf2e65": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"a64f617952e04410b8c6275cf6eb4e28": {
"model_module": "@jupyter-widgets/controls",
"model_name": "IntProgressModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "IntProgressModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "ProgressView",
"bar_style": "success",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_aaf4d725a6e042198a1b63243c0b716f",
"max": 1,
"min": 0,
"orientation": "horizontal",
"style": "IPY_MODEL_2eb6e9b94d2a44c699a2284b38d5df70",
"value": 1
}
},
"0922ce837deb4f208e1f28e25492b7c8": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "HTMLView",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_109c0ef14c2f48fd9119bcda9620f2b0",
"placeholder": "",
"style": "IPY_MODEL_c9ba04b4eed44a04a9aeaeaa8a44ecfa",
"value": "8192it [00:00, 43677.89it/s]"
}
},
"2eb6e9b94d2a44c699a2284b38d5df70": {
"model_module": "@jupyter-widgets/controls",
"model_name": "ProgressStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "ProgressStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"bar_color": null,
"description_width": ""
}
},
"aaf4d725a6e042198a1b63243c0b716f": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"c9ba04b4eed44a04a9aeaeaa8a44ecfa": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "DescriptionStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"description_width": ""
}
},
"109c0ef14c2f48fd9119bcda9620f2b0": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
}
}
}
},
"cells": [
{
"cell_type": "code",
"metadata": {
"colab_type": "code",
"id": "tHTDX9M9g_iq",
"colab": {}
},
"source": [
"from __future__ import print_function\n",
"import torch\n",
"import torch.nn as nn\n",
"import torch.nn.functional as F\n",
"import torch.optim as optim\n",
"from torchvision import datasets, transforms"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"colab_type": "code",
"id": "kY7jPu9bhUji",
"colab": {}
},
"source": [
"# Train Phase transformations\n",
"train_transforms = transforms.Compose([\n",
" # transforms.Resize((28, 28)),\n",
" # transforms.ColorJitter(brightness=0.10, contrast=0.1, saturation=0.10, hue=0.1),\n",
" transforms.RandomRotation((-7.0, 7.0), fill=(1,)),\n",
" transforms.ToTensor(),\n",
" transforms.Normalize((0.1307,), (0.3081,)) # The mean and std have to be sequences (e.g., tuples), therefore you should add a comma after the values. \n",
" # Note the difference between (0.1307) and (0.1307,)\n",
" ])\n",
"\n",
"# Test Phase transformations\n",
"test_transforms = transforms.Compose([\n",
" # transforms.Resize((28, 28)),\n",
" # transforms.ColorJitter(brightness=0.10, contrast=0.1, saturation=0.10, hue=0.1),\n",
" transforms.ToTensor(),\n",
" transforms.Normalize((0.1307,), (0.3081,))\n",
" ])"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"colab_type": "code",
"id": "oFQFDvVwhYkL",
"outputId": "bac382ef-d6c8-4ac0-85ea-790981405ef2",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 383,
"referenced_widgets": [
"9cd8896b7dd34a87a99eee8fe6b9696f",
"15767740c5f244d4b5cee67c0805e845",
"1c73b0d38f75415abb42719ddd575514",
"e7823cf07812486489aae4b9acd60037",
"d7f205d9c7534b168a7d34c1db553e99",
"250fce83a7ea471fa4980abab7410f37",
"c3d463df14a94069a8ecf252ab1fbcb4",
"0ffc1d10d3824646a71697a6ad19e77e",
"ded66cf881e04769992669ef97e81de8",
"4b3491b1fd644a2b94320f16371f9db2",
"6370d4c3e29f464d9369a4e1584895b0",
"afc6bffb76dd412abcc4bfbc27c95943",
"39d55bc2e77a42d6a0e7429422532c10",
"821ac6d3f2ac4b78ac309f3fc92918b6",
"c01169a89af1436ba347abe350e726a5",
"288756d3fc9844acb6fd36107b1b2b41",
"195384495f93466fac89c8f911014da5",
"ea6a26003ef248f4bd94d7622222d5b3",
"3e72d9d211da4f878e4977e7b6413d11",
"8b848ba7765d49e6bb915248c3923424",
"68765c521fd646aabc6bfee66c82cc37",
"8941f3c480614fd582c59ab57bf469fc",
"683a1732e1fa45c78bde39c3e1ac29d1",
"b5f1f660daf94c8286931e8c52c09c9b",
"3fb3f03ac0154699916e8706210fb08f",
"e5862969092c48f2a9a77f1f05bf2e65",
"a64f617952e04410b8c6275cf6eb4e28",
"0922ce837deb4f208e1f28e25492b7c8",
"2eb6e9b94d2a44c699a2284b38d5df70",
"aaf4d725a6e042198a1b63243c0b716f",
"c9ba04b4eed44a04a9aeaeaa8a44ecfa",
"109c0ef14c2f48fd9119bcda9620f2b0"
]
}
},
"source": [
"train = datasets.MNIST('./data', train=True, download=True, transform=train_transforms)\n",
"test = datasets.MNIST('./data', train=False, download=True, transform=test_transforms)"
],
"execution_count": 0,
"outputs": [
{
"output_type": "stream",
"text": [
"Downloading http://yann.lecun.com/exdb/mnist/train-images-idx3-ubyte.gz to ./data/MNIST/raw/train-images-idx3-ubyte.gz\n"
],
"name": "stdout"
},
{
"output_type": "display_data",
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "9cd8896b7dd34a87a99eee8fe6b9696f",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=1, bar_style='info', max=1), HTML(value='')))"
]
},
"metadata": {
"tags": []
}
},
{
"output_type": "stream",
"text": [
"\n",
"Extracting ./data/MNIST/raw/train-images-idx3-ubyte.gz to ./data/MNIST/raw\n",
"Downloading http://yann.lecun.com/exdb/mnist/train-labels-idx1-ubyte.gz to ./data/MNIST/raw/train-labels-idx1-ubyte.gz\n"
],
"name": "stdout"
},
{
"output_type": "display_data",
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "ded66cf881e04769992669ef97e81de8",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=1, bar_style='info', max=1), HTML(value='')))"
]
},
"metadata": {
"tags": []
}
},
{
"output_type": "stream",
"text": [
"\n",
"Extracting ./data/MNIST/raw/train-labels-idx1-ubyte.gz to ./data/MNIST/raw\n",
"Downloading http://yann.lecun.com/exdb/mnist/t10k-images-idx3-ubyte.gz to ./data/MNIST/raw/t10k-images-idx3-ubyte.gz\n"
],
"name": "stdout"
},
{
"output_type": "display_data",
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "195384495f93466fac89c8f911014da5",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=1, bar_style='info', max=1), HTML(value='')))"
]
},
"metadata": {
"tags": []
}
},
{
"output_type": "stream",
"text": [
"\n",
"Extracting ./data/MNIST/raw/t10k-images-idx3-ubyte.gz to ./data/MNIST/raw\n",
"Downloading http://yann.lecun.com/exdb/mnist/t10k-labels-idx1-ubyte.gz to ./data/MNIST/raw/t10k-labels-idx1-ubyte.gz\n"
],
"name": "stdout"
},
{
"output_type": "display_data",
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "3fb3f03ac0154699916e8706210fb08f",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"HBox(children=(IntProgress(value=1, bar_style='info', max=1), HTML(value='')))"
]
},
"metadata": {
"tags": []
}
},
{
"output_type": "stream",
"text": [
"\n",
"Extracting ./data/MNIST/raw/t10k-labels-idx1-ubyte.gz to ./data/MNIST/raw\n",
"Processing...\n",
"Done!\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"colab_type": "code",
"id": "J2ukHjRzhfyR",
"outputId": "dea98d2e-2be5-40b7-d782-069fe94d06e6",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 34
}
},
"source": [
"SEED = 1\n",
"\n",
"# CUDA?\n",
"cuda = torch.cuda.is_available()\n",
"print(\"CUDA Available?\", cuda)\n",
"\n",
"# For reproducibility\n",
"torch.manual_seed(SEED)\n",
"\n",
"if cuda:\n",
" torch.cuda.manual_seed(SEED)\n",
"\n",
"# dataloader arguments - something you'll fetch these from cmdprmt\n",
"dataloader_args = dict(shuffle=True, batch_size=128, num_workers=4, pin_memory=True) if cuda else dict(shuffle=True, batch_size=64)\n",
"\n",
"# train dataloader\n",
"train_loader = torch.utils.data.DataLoader(train, **dataloader_args)\n",
"\n",
"# test dataloader\n",
"test_loader = torch.utils.data.DataLoader(test, **dataloader_args)"
],
"execution_count": 0,
"outputs": [
{
"output_type": "stream",
"text": [
"CUDA Available? True\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"colab_type": "code",
"id": "i7Aj-6-dhi3K",
"colab": {}
},
"source": [
"import torch.nn.functional as F\n",
"dropout_value = 0.1\n",
"class Net(nn.Module):\n",
" def __init__(self):\n",
" super(Net, self).__init__()\n",
" # Input Block\n",
" self.convblock1 = nn.Sequential(\n",
" nn.Conv2d(in_channels=1, out_channels=8, kernel_size=(3, 3), padding=0, bias=False),\n",
" nn.ReLU(),\n",
" nn.BatchNorm2d(8),\n",
" nn.Dropout(dropout_value)\n",
" ) # output_size = 26\n",
"\n",
" # CONVOLUTION BLOCK 1\n",
" self.convblock2 = nn.Sequential(\n",
" nn.Conv2d(in_channels=8, out_channels=8, kernel_size=(3, 3), padding=0, bias=False),\n",
" nn.ReLU(),\n",
" nn.BatchNorm2d(8),\n",
" nn.Dropout(dropout_value)\n",
" \n",
" ) # output_size = 24\n",
" \n",
" self.convblock3 = nn.Sequential(\n",
" nn.Conv2d(in_channels=8, out_channels=16, kernel_size=(3, 3), padding=0, bias=False),\n",
" nn.ReLU(),\n",
" nn.BatchNorm2d(16),\n",
" nn.Dropout(dropout_value)\n",
" ) # output_size = 22\n",
"\n",
" # TRANSITION BLOCK 1\n",
" self.pool1 = nn.MaxPool2d(2, 2)\n",
" # output_size = 11\n",
" self.convblock4 = nn.Sequential(\n",
" nn.Conv2d(in_channels=16, out_channels=32, kernel_size=(3, 3), padding=0, bias=False),\n",
" nn.ReLU(),\n",
" nn.BatchNorm2d(32),\n",
" nn.Dropout(dropout_value)\n",
" ) # output_size = 11\n",
" \n",
" # CONVOLUTION BLOCK 2\n",
" self.convblock5 = nn.Sequential(\n",
" nn.Conv2d(in_channels=32, out_channels=16, kernel_size=(1, 1), padding=0, bias=False),\n",
" nn.BatchNorm2d(16),\n",
" nn.ReLU(),\n",
" nn.Dropout(dropout_value)\n",
" \n",
" ) # output_size = 9\n",
" #self.pool2 = nn.MaxPool2d(2, 2)\n",
" self.convblock6 = nn.Sequential(\n",
" nn.Conv2d(in_channels=16, out_channels=16, kernel_size=(3, 3), padding=0, bias=False),\n",
" nn.ReLU(),\n",
" nn.BatchNorm2d(16),\n",
" nn.Dropout(dropout_value)\n",
" ) # output_size = 7\n",
"\n",
" \n",
"\n",
" self.gap = nn.Sequential(\n",
" nn.AvgPool2d(kernel_size=6)\n",
" ) # output_size = 1\n",
"\n",
" # OUTPUT BLOCK\n",
" self.convblock7 = nn.Sequential(\n",
" nn.Conv2d(in_channels=16, out_channels=10, kernel_size=(1, 1), padding=0, bias=False),\n",
" #nn.BatchNorm2d(16),\n",
" #nn.ReLU(),\n",
" #nn.Dropout(dropout_value)\n",
" #) # output_size = 7\n",
"\n",
" #self.convblock8 = nn.Sequential(\n",
" #nn.Conv2d(in_channels=16, out_channels=10, kernel_size=(1, 1), padding=0, bias=False),\n",
" # nn.BatchNorm2d(10), NEVER\n",
" # nn.ReLU() NEVER!\n",
" ) # output_size = 1\n",
"\n",
" self.dropout = nn.Dropout(dropout_value)\n",
"\n",
" def forward(self, x):\n",
" x = self.convblock1(x)\n",
" x = self.convblock2(x)\n",
" x = self.pool1(x)\n",
" x = self.convblock3(x)\n",
" #x = self.pool1(x)\n",
" #x = self.dropout(x)\n",
" \n",
" x = self.convblock4(x)\n",
" \n",
" x = self.convblock5(x)\n",
" #x = self.pool2(x)\n",
" x = self.convblock6(x)\n",
" \n",
" #x = self.dropout(x)\n",
" x = self.gap(x) \n",
" x = self.convblock7(x)\n",
" #x = self.convblock8(x)\n",
"\n",
" x = x.view(-1, 10)\n",
" return F.log_softmax(x, dim=-1)"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"colab_type": "code",
"id": "E_8sh7CBhnGK",
"outputId": "a4c43201-2d0d-447c-87c0-44775229ff65",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 731
}
},
"source": [
"!pip install torchsummary\n",
"from torchsummary import summary\n",
"use_cuda = torch.cuda.is_available()\n",
"device = torch.device(\"cuda\" if use_cuda else \"cpu\")\n",
"print(device)\n",
"model = Net().to(device)\n",
"summary(model, input_size=(1, 28, 28))"
],
"execution_count": 0,
"outputs": [
{
"output_type": "stream",
"text": [
"Requirement already satisfied: torchsummary in /usr/local/lib/python3.6/dist-packages (1.5.1)\n",
"cuda\n",
"----------------------------------------------------------------\n",
" Layer (type) Output Shape Param #\n",
"================================================================\n",
" Conv2d-1 [-1, 8, 26, 26] 72\n",
" ReLU-2 [-1, 8, 26, 26] 0\n",
" BatchNorm2d-3 [-1, 8, 26, 26] 16\n",
" Dropout-4 [-1, 8, 26, 26] 0\n",
" Conv2d-5 [-1, 8, 24, 24] 576\n",
" ReLU-6 [-1, 8, 24, 24] 0\n",
" BatchNorm2d-7 [-1, 8, 24, 24] 16\n",
" Dropout-8 [-1, 8, 24, 24] 0\n",
" MaxPool2d-9 [-1, 8, 12, 12] 0\n",
" Conv2d-10 [-1, 16, 10, 10] 1,152\n",
" ReLU-11 [-1, 16, 10, 10] 0\n",
" BatchNorm2d-12 [-1, 16, 10, 10] 32\n",
" Dropout-13 [-1, 16, 10, 10] 0\n",
" Conv2d-14 [-1, 32, 8, 8] 4,608\n",
" ReLU-15 [-1, 32, 8, 8] 0\n",
" BatchNorm2d-16 [-1, 32, 8, 8] 64\n",
" Dropout-17 [-1, 32, 8, 8] 0\n",
" Conv2d-18 [-1, 16, 8, 8] 512\n",
" BatchNorm2d-19 [-1, 16, 8, 8] 32\n",
" ReLU-20 [-1, 16, 8, 8] 0\n",
" Dropout-21 [-1, 16, 8, 8] 0\n",
" Conv2d-22 [-1, 16, 6, 6] 2,304\n",
" ReLU-23 [-1, 16, 6, 6] 0\n",
" BatchNorm2d-24 [-1, 16, 6, 6] 32\n",
" Dropout-25 [-1, 16, 6, 6] 0\n",
" AvgPool2d-26 [-1, 16, 1, 1] 0\n",
" Conv2d-27 [-1, 10, 1, 1] 160\n",
"================================================================\n",
"Total params: 9,576\n",
"Trainable params: 9,576\n",
"Non-trainable params: 0\n",
"----------------------------------------------------------------\n",
"Input size (MB): 0.00\n",
"Forward/backward pass size (MB): 0.47\n",
"Params size (MB): 0.04\n",
"Estimated Total Size (MB): 0.51\n",
"----------------------------------------------------------------\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"colab_type": "code",
"id": "mA29-cgbhoPB",
"colab": {}
},
"source": [
"from tqdm import tqdm\n",
"\n",
"train_losses = []\n",
"test_losses = []\n",
"train_acc = []\n",
"test_acc = []\n",
"\n",
"def train(model, device, train_loader, optimizer, epoch):\n",
" model.train()\n",
" pbar = tqdm(train_loader)\n",
" correct = 0\n",
" processed = 0\n",
" criterion = nn.CrossEntropyLoss().to(device)\n",
" for batch_idx, (data, target) in enumerate(pbar):\n",
" # get samples\n",
" data, target = data.to(device), target.to(device)\n",
"\n",
" # Init\n",
" optimizer.zero_grad()\n",
" # In PyTorch, we need to set the gradients to zero before starting to do backpropragation because PyTorch accumulates the gradients on subsequent backward passes. \n",
" # Because of this, when you start your training loop, ideally you should zero out the gradients so that you do the parameter update correctly.\n",
"\n",
" # Predict\n",
" y_pred = model(data)\n",
"\n",
" # Calculate loss\n",
" regularization_loss = 0\n",
" for param in model.parameters():\n",
" regularization_loss += torch.sum(abs(param))\n",
" classify_loss = criterion(y_pred,target)\n",
"\n",
" #loss = F.nll_loss(y_pred, target)\n",
" factor = 0.0005\n",
" loss = classify_loss + factor * regularization_loss\n",
"\n",
" train_losses.append(loss)\n",
"\n",
" # Backpropagation\n",
" loss.backward()\n",
" optimizer.step()\n",
"\n",
" # Update pbar-tqdm\n",
" \n",
" pred = y_pred.argmax(dim=1, keepdim=True) # get the index of the max log-probability\n",
" correct += pred.eq(target.view_as(pred)).sum().item()\n",
" processed += len(data)\n",
"\n",
" pbar.set_description(desc= f'Loss={loss.item()} Batch_id={batch_idx} Accuracy={100*correct/processed:0.2f}')\n",
" train_acc.append(100*correct/processed)\n",
"\n",
"def test(model, device, test_loader):\n",
" model.eval()\n",
" test_loss = 0\n",
" correct = 0\n",
" with torch.no_grad():\n",
" for data, target in test_loader:\n",
" data, target = data.to(device), target.to(device)\n",
" output = model(data)\n",
" test_loss += F.nll_loss(output, target, reduction='sum').item() # sum up batch loss\n",
" pred = output.argmax(dim=1, keepdim=True) # get the index of the max log-probability\n",
" correct += pred.eq(target.view_as(pred)).sum().item()\n",
"\n",
" test_loss /= len(test_loader.dataset)\n",
" test_losses.append(test_loss)\n",
"\n",
" print('\\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.2f}%)\\n'.format(\n",
" test_loss, correct, len(test_loader.dataset),\n",
" 100. * correct / len(test_loader.dataset)))\n",
" \n",
" test_acc.append(100. * correct / len(test_loader.dataset))"
],
"execution_count": 0,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"colab_type": "code",
"id": "Skc_dEVnhsmK",
"outputId": "59ff4384-87e9-4c2d-be08-3200e835f38d",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1000
}
},
"source": [
"from torch.optim.lr_scheduler import StepLR\n",
"\n",
"model = Net().to(device)\n",
"optimizer = optim.SGD(model.parameters(), lr=0.05, weight_decay = 0, momentum=0.9, dampening = 0, nesterov = False)\n",
"scheduler = StepLR(optimizer, step_size=6, gamma=0.5)\n",
"\n",
"EPOCHS = 40\n",
"\n",
"for epoch in range(EPOCHS):\n",
" print(\"EPOCH:\", epoch)\n",
" train(model, device, train_loader, optimizer, epoch)\n",
" test(model, device, test_loader)"
],
"execution_count": 0,
"outputs": [
{
"output_type": "stream",
"text": [
"\r 0%| | 0/469 [00:00<?, ?it/s]"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"EPOCH: 0\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"Loss=0.3718750476837158 Batch_id=468 Accuracy=91.96: 100%|██████████| 469/469 [00:14<00:00, 31.45it/s]\n",
" 0%| | 0/469 [00:00<?, ?it/s]"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"\n",
"Test set: Average loss: 0.0887, Accuracy: 9735/10000 (97.35%)\n",
"\n",
"EPOCH: 1\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"Loss=0.27893275022506714 Batch_id=468 Accuracy=96.98: 100%|██████████| 469/469 [00:14<00:00, 31.80it/s]\n",
" 0%| | 0/469 [00:00<?, ?it/s]"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"\n",
"Test set: Average loss: 0.0581, Accuracy: 9827/10000 (98.27%)\n",
"\n",
"EPOCH: 2\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"Loss=0.3314529061317444 Batch_id=468 Accuracy=97.14: 100%|██████████| 469/469 [00:15<00:00, 33.91it/s]\n",
" 0%| | 0/469 [00:00<?, ?it/s]"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"\n",
"Test set: Average loss: 0.0701, Accuracy: 9783/10000 (97.83%)\n",
"\n",
"EPOCH: 3\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"Loss=0.3042295575141907 Batch_id=468 Accuracy=97.17: 100%|██████████| 469/469 [00:14<00:00, 38.39it/s]\n",
" 0%| | 0/469 [00:00<?, ?it/s]"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"\n",
"Test set: Average loss: 0.0771, Accuracy: 9769/10000 (97.69%)\n",
"\n",
"EPOCH: 4\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"Loss=0.3286988437175751 Batch_id=468 Accuracy=97.23: 100%|██████████| 469/469 [00:14<00:00, 32.08it/s]\n",
" 0%| | 0/469 [00:00<?, ?it/s]"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"\n",
"Test set: Average loss: 0.0887, Accuracy: 9707/10000 (97.07%)\n",
"\n",
"EPOCH: 5\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"Loss=0.2915857434272766 Batch_id=468 Accuracy=97.19: 100%|██████████| 469/469 [00:14<00:00, 32.30it/s]\n",
" 0%| | 0/469 [00:00<?, ?it/s]"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"\n",
"Test set: Average loss: 0.0656, Accuracy: 9781/10000 (97.81%)\n",
"\n",
"EPOCH: 6\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"Loss=0.28575822710990906 Batch_id=468 Accuracy=97.18: 100%|██████████| 469/469 [00:14<00:00, 31.55it/s]\n",
" 0%| | 0/469 [00:00<?, ?it/s]"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"\n",
"Test set: Average loss: 0.1040, Accuracy: 9650/10000 (96.50%)\n",
"\n",
"EPOCH: 7\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"Loss=0.3060661256313324 Batch_id=468 Accuracy=97.23: 100%|██████████| 469/469 [00:14<00:00, 32.00it/s]\n",
" 0%| | 0/469 [00:00<?, ?it/s]"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"\n",
"Test set: Average loss: 0.0648, Accuracy: 9812/10000 (98.12%)\n",
"\n",
"EPOCH: 8\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"Loss=0.3298959732055664 Batch_id=468 Accuracy=97.28: 100%|██████████| 469/469 [00:14<00:00, 32.70it/s]\n",
" 0%| | 0/469 [00:00<?, ?it/s]"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"\n",
"Test set: Average loss: 0.0697, Accuracy: 9799/10000 (97.99%)\n",
"\n",
"EPOCH: 9\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"Loss=0.260184109210968 Batch_id=468 Accuracy=97.15: 100%|██████████| 469/469 [00:14<00:00, 32.57it/s]\n",
" 0%| | 0/469 [00:00<?, ?it/s]"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"\n",
"Test set: Average loss: 0.0559, Accuracy: 9844/10000 (98.44%)\n",
"\n",
"EPOCH: 10\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"Loss=0.28738611936569214 Batch_id=468 Accuracy=97.23: 100%|██████████| 469/469 [00:14<00:00, 40.11it/s]\n",
" 0%| | 0/469 [00:00<?, ?it/s]"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"\n",
"Test set: Average loss: 0.0688, Accuracy: 9788/10000 (97.88%)\n",
"\n",
"EPOCH: 11\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"Loss=0.2886216640472412 Batch_id=468 Accuracy=97.16: 100%|██████████| 469/469 [00:14<00:00, 32.72it/s]\n",
" 0%| | 0/469 [00:00<?, ?it/s]"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"\n",
"Test set: Average loss: 0.1303, Accuracy: 9586/10000 (95.86%)\n",
"\n",
"EPOCH: 12\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"Loss=0.3454681634902954 Batch_id=468 Accuracy=97.19: 100%|██████████| 469/469 [00:14<00:00, 33.10it/s]\n",
" 0%| | 0/469 [00:00<?, ?it/s]"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"\n",
"Test set: Average loss: 0.0625, Accuracy: 9812/10000 (98.12%)\n",
"\n",
"EPOCH: 13\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"Loss=0.3431510627269745 Batch_id=468 Accuracy=97.26: 100%|██████████| 469/469 [00:14<00:00, 32.87it/s]\n",
" 0%| | 0/469 [00:00<?, ?it/s]"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"\n",
"Test set: Average loss: 0.1939, Accuracy: 9388/10000 (93.88%)\n",
"\n",
"EPOCH: 14\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"Loss=0.46529337763786316 Batch_id=468 Accuracy=97.23: 100%|██████████| 469/469 [00:14<00:00, 32.66it/s]\n",
" 0%| | 0/469 [00:00<?, ?it/s]"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"\n",
"Test set: Average loss: 0.0888, Accuracy: 9730/10000 (97.30%)\n",
"\n",
"EPOCH: 15\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"Loss=0.24989710748195648 Batch_id=468 Accuracy=97.20: 100%|██████████| 469/469 [00:13<00:00, 39.19it/s]\n",
" 0%| | 0/469 [00:00<?, ?it/s]"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"\n",
"Test set: Average loss: 0.0870, Accuracy: 9700/10000 (97.00%)\n",
"\n",
"EPOCH: 16\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"Loss=0.28807756304740906 Batch_id=468 Accuracy=97.13: 100%|██████████| 469/469 [00:13<00:00, 33.55it/s]\n",
" 0%| | 0/469 [00:00<?, ?it/s]"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"\n",
"Test set: Average loss: 0.0729, Accuracy: 9776/10000 (97.76%)\n",
"\n",
"EPOCH: 17\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"Loss=0.23334521055221558 Batch_id=468 Accuracy=97.30: 100%|██████████| 469/469 [00:14<00:00, 33.08it/s]\n",
" 0%| | 0/469 [00:00<?, ?it/s]"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"\n",
"Test set: Average loss: 0.0745, Accuracy: 9764/10000 (97.64%)\n",
"\n",
"EPOCH: 18\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"Loss=0.2260483205318451 Batch_id=468 Accuracy=97.18: 100%|██████████| 469/469 [00:13<00:00, 40.73it/s]\n",
" 0%| | 0/469 [00:00<?, ?it/s]"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"\n",
"Test set: Average loss: 0.1065, Accuracy: 9652/10000 (96.52%)\n",
"\n",
"EPOCH: 19\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"Loss=0.23472583293914795 Batch_id=468 Accuracy=97.31: 100%|██████████| 469/469 [00:13<00:00, 34.46it/s]\n",
" 0%| | 0/469 [00:00<?, ?it/s]"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"\n",
"Test set: Average loss: 0.0815, Accuracy: 9743/10000 (97.43%)\n",
"\n",
"EPOCH: 20\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"Loss=0.24220630526542664 Batch_id=468 Accuracy=97.20: 100%|██████████| 469/469 [00:13<00:00, 34.64it/s]\n",
" 0%| | 0/469 [00:00<?, ?it/s]"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"\n",
"Test set: Average loss: 0.0594, Accuracy: 9815/10000 (98.15%)\n",
"\n",
"EPOCH: 21\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"Loss=0.2299569696187973 Batch_id=468 Accuracy=97.24: 100%|██████████| 469/469 [00:14<00:00, 33.16it/s]\n",
" 0%| | 0/469 [00:00<?, ?it/s]"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"\n",
"Test set: Average loss: 0.0750, Accuracy: 9767/10000 (97.67%)\n",
"\n",
"EPOCH: 22\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"Loss=0.2849569320678711 Batch_id=468 Accuracy=97.18: 100%|██████████| 469/469 [00:13<00:00, 34.25it/s]\n",
" 0%| | 0/469 [00:00<?, ?it/s]"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"\n",
"Test set: Average loss: 0.0646, Accuracy: 9790/10000 (97.90%)\n",
"\n",
"EPOCH: 23\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"Loss=0.2913033366203308 Batch_id=468 Accuracy=97.19: 100%|██████████| 469/469 [00:13<00:00, 34.24it/s]\n",
" 0%| | 0/469 [00:00<?, ?it/s]"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"\n",
"Test set: Average loss: 0.0718, Accuracy: 9765/10000 (97.65%)\n",
"\n",
"EPOCH: 24\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"Loss=0.2507942318916321 Batch_id=468 Accuracy=97.23: 100%|██████████| 469/469 [00:13<00:00, 40.82it/s]\n",
" 0%| | 0/469 [00:00<?, ?it/s]"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"\n",
"Test set: Average loss: 0.1179, Accuracy: 9617/10000 (96.17%)\n",
"\n",
"EPOCH: 25\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"Loss=0.2674029469490051 Batch_id=468 Accuracy=97.35: 100%|██████████| 469/469 [00:14<00:00, 33.18it/s]\n",
" 0%| | 0/469 [00:00<?, ?it/s]"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"\n",
"Test set: Average loss: 0.0628, Accuracy: 9829/10000 (98.29%)\n",
"\n",
"EPOCH: 26\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"Loss=0.2965560853481293 Batch_id=468 Accuracy=97.26: 100%|██████████| 469/469 [00:13<00:00, 34.26it/s]\n",
" 0%| | 0/469 [00:00<?, ?it/s]"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"\n",
"Test set: Average loss: 0.0900, Accuracy: 9715/10000 (97.15%)\n",
"\n",
"EPOCH: 27\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"Loss=0.2190781980752945 Batch_id=468 Accuracy=97.30: 100%|██████████| 469/469 [00:13<00:00, 33.96it/s]\n",
" 0%| | 0/469 [00:00<?, ?it/s]"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"\n",
"Test set: Average loss: 0.0913, Accuracy: 9726/10000 (97.26%)\n",
"\n",
"EPOCH: 28\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"Loss=0.26742902398109436 Batch_id=468 Accuracy=97.21: 100%|██████████| 469/469 [00:13<00:00, 34.63it/s]\n",
" 0%| | 0/469 [00:00<?, ?it/s]"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"\n",
"Test set: Average loss: 0.0673, Accuracy: 9787/10000 (97.87%)\n",
"\n",
"EPOCH: 29\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"Loss=0.27080264687538147 Batch_id=468 Accuracy=97.16: 100%|██████████| 469/469 [00:14<00:00, 33.25it/s]\n",
" 0%| | 0/469 [00:00<?, ?it/s]"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"\n",
"Test set: Average loss: 0.0803, Accuracy: 9744/10000 (97.44%)\n",
"\n",
"EPOCH: 30\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"Loss=0.3085210621356964 Batch_id=468 Accuracy=97.31: 100%|██████████| 469/469 [00:13<00:00, 34.79it/s]\n",
" 0%| | 0/469 [00:00<?, ?it/s]"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"\n",
"Test set: Average loss: 0.0542, Accuracy: 9828/10000 (98.28%)\n",
"\n",
"EPOCH: 31\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"Loss=0.3690635859966278 Batch_id=468 Accuracy=97.30: 100%|██████████| 469/469 [00:13<00:00, 35.09it/s]\n",
" 0%| | 0/469 [00:00<?, ?it/s]"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"\n",
"Test set: Average loss: 0.0670, Accuracy: 9785/10000 (97.85%)\n",
"\n",
"EPOCH: 32\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"Loss=0.24982883036136627 Batch_id=468 Accuracy=97.10: 100%|██████████| 469/469 [00:13<00:00, 35.34it/s]\n",
" 0%| | 0/469 [00:00<?, ?it/s]"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"\n",
"Test set: Average loss: 0.0641, Accuracy: 9801/10000 (98.01%)\n",
"\n",
"EPOCH: 33\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"Loss=0.27397793531417847 Batch_id=468 Accuracy=97.26: 100%|██████████| 469/469 [00:14<00:00, 33.20it/s]\n",
" 0%| | 0/469 [00:00<?, ?it/s]"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"\n",
"Test set: Average loss: 0.1059, Accuracy: 9688/10000 (96.88%)\n",
"\n",
"EPOCH: 34\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"Loss=0.40837812423706055 Batch_id=468 Accuracy=97.11: 100%|██████████| 469/469 [00:13<00:00, 34.62it/s]\n",
" 0%| | 0/469 [00:00<?, ?it/s]"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"\n",
"Test set: Average loss: 0.0772, Accuracy: 9768/10000 (97.68%)\n",
"\n",
"EPOCH: 35\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"Loss=0.25087428092956543 Batch_id=468 Accuracy=97.25: 100%|██████████| 469/469 [00:13<00:00, 35.71it/s]\n",
" 0%| | 0/469 [00:00<?, ?it/s]"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"\n",
"Test set: Average loss: 0.0606, Accuracy: 9821/10000 (98.21%)\n",
"\n",
"EPOCH: 36\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"Loss=0.2785159945487976 Batch_id=468 Accuracy=97.17: 100%|██████████| 469/469 [00:13<00:00, 34.68it/s]\n",
" 0%| | 0/469 [00:00<?, ?it/s]"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"\n",
"Test set: Average loss: 0.0905, Accuracy: 9711/10000 (97.11%)\n",
"\n",
"EPOCH: 37\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"Loss=0.236347034573555 Batch_id=468 Accuracy=97.31: 100%|██████████| 469/469 [00:14<00:00, 33.43it/s]\n",
" 0%| | 0/469 [00:00<?, ?it/s]"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"\n",
"Test set: Average loss: 0.1006, Accuracy: 9672/10000 (96.72%)\n",
"\n",
"EPOCH: 38\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"Loss=0.25926482677459717 Batch_id=468 Accuracy=97.26: 100%|██████████| 469/469 [00:13<00:00, 35.00it/s]\n",
" 0%| | 0/469 [00:00<?, ?it/s]"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"\n",
"Test set: Average loss: 0.1013, Accuracy: 9695/10000 (96.95%)\n",
"\n",
"EPOCH: 39\n"
],
"name": "stdout"
},
{
"output_type": "stream",
"text": [
"Loss=0.26961827278137207 Batch_id=468 Accuracy=97.19: 100%|██████████| 469/469 [00:13<00:00, 42.72it/s]\n"
],
"name": "stderr"
},
{
"output_type": "stream",
"text": [
"\n",
"Test set: Average loss: 0.0879, Accuracy: 9721/10000 (97.21%)\n",
"\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"colab_type": "code",
"id": "N046WTqIhtdh",
"outputId": "080204cb-b352-4dab-eb77-b0b88f9133ae",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 624
}
},
"source": [
"%matplotlib inline\n",
"import matplotlib.pyplot as plt\n",
"\n",
"fig, axs = plt.subplots(2,2,figsize=(15,10))\n",
"axs[0, 0].plot(train_losses)\n",
"axs[0, 0].set_title(\"Training Loss\")\n",
"axs[1, 0].plot(train_acc[4000:])\n",
"axs[1, 0].set_title(\"Training Accuracy\")\n",
"axs[0, 1].plot(test_losses)\n",
"axs[0, 1].set_title(\"Test Loss\")\n",
"axs[1, 1].plot(test_acc)\n",
"axs[1, 1].set_title(\"Test Accuracy\")"
],
"execution_count": 0,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"Text(0.5, 1.0, 'Test Accuracy')"
]
},
"metadata": {
"tags": []
},
"execution_count": 11
},
{
"output_type": "display_data",
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAA2oAAAJOCAYAAADGYfSfAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nkiTVzP8HpVu7uPHxyvkAAAAASUVORK5CYII=\n",
"text/plain": [
"<Figure size 1080x720 with 4 Axes>"
]
},
"metadata": {
"tags": []
}
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "0CJ8BMqrCYNU",
"colab_type": "text"
},
"source": [
"Submitted by G Uday Kiran and V Srilakshmi"
]
}
]
}