\n",
@@ -550,7 +550,7 @@
},
{
"cell_type": "markdown",
- "id": "b93071a2",
+ "id": "71b2e6fa",
"metadata": {},
"source": [
"
Checkpoint 2
\n",
@@ -570,7 +570,7 @@
},
{
"cell_type": "markdown",
- "id": "e9f2b7ae",
+ "id": "e0966908",
"metadata": {
"lines_to_next_cell": 0
},
@@ -598,7 +598,7 @@
},
{
"cell_type": "markdown",
- "id": "92223fdc",
+ "id": "50bfe53d",
"metadata": {
"lines_to_next_cell": 0,
"tags": []
@@ -621,7 +621,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "5a72db0b",
+ "id": "b1ab5f6d",
"metadata": {},
"outputs": [],
"source": [
@@ -653,7 +653,7 @@
},
{
"cell_type": "markdown",
- "id": "01335c40",
+ "id": "7029ce21",
"metadata": {
"lines_to_next_cell": 0
},
@@ -668,7 +668,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "8d0f0203",
+ "id": "48bc8945",
"metadata": {
"lines_to_next_cell": 0,
"tags": [
@@ -689,7 +689,7 @@
},
{
"cell_type": "markdown",
- "id": "186f40a5",
+ "id": "156d8774",
"metadata": {
"tags": []
},
@@ -704,7 +704,7 @@
},
{
"cell_type": "markdown",
- "id": "af4cf127",
+ "id": "48a541a1",
"metadata": {
"lines_to_next_cell": 0,
"tags": []
@@ -721,7 +721,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "94f07b70",
+ "id": "433257a6",
"metadata": {
"lines_to_next_cell": 0,
"tags": [
@@ -735,7 +735,7 @@
},
{
"cell_type": "markdown",
- "id": "c2a072a4",
+ "id": "b16b319e",
"metadata": {
"lines_to_next_cell": 0
},
@@ -746,7 +746,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "f7bb217b",
+ "id": "1e85b7b2",
"metadata": {},
"outputs": [],
"source": [
@@ -756,7 +756,7 @@
},
{
"cell_type": "markdown",
- "id": "dfdd1272",
+ "id": "dc1c55cf",
"metadata": {
"lines_to_next_cell": 0,
"tags": []
@@ -774,7 +774,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "7ddd581a",
+ "id": "33e0ea83",
"metadata": {
"lines_to_next_cell": 0
},
@@ -786,7 +786,7 @@
},
{
"cell_type": "markdown",
- "id": "2f7fe43c",
+ "id": "6bbe594d",
"metadata": {
"lines_to_next_cell": 0,
"tags": []
@@ -805,7 +805,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "f01095a7",
+ "id": "7b5f7065",
"metadata": {},
"outputs": [],
"source": [
@@ -814,7 +814,7 @@
},
{
"cell_type": "markdown",
- "id": "bad091aa",
+ "id": "c4886cf1",
"metadata": {
"lines_to_next_cell": 0,
"tags": []
@@ -830,7 +830,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "e49c55e0",
+ "id": "1f2d9558",
"metadata": {},
"outputs": [],
"source": [
@@ -839,7 +839,7 @@
},
{
"cell_type": "markdown",
- "id": "af990b9a",
+ "id": "6632b7c6",
"metadata": {
"lines_to_next_cell": 0,
"tags": []
@@ -851,7 +851,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "291f2062",
+ "id": "2b336a53",
"metadata": {},
"outputs": [],
"source": [
@@ -864,7 +864,7 @@
},
{
"cell_type": "markdown",
- "id": "919aea73",
+ "id": "b7c49115",
"metadata": {
"lines_to_next_cell": 0,
"tags": []
@@ -878,7 +878,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "26f2a9c1",
+ "id": "e076c809",
"metadata": {},
"outputs": [],
"source": [
@@ -890,7 +890,7 @@
},
{
"cell_type": "markdown",
- "id": "54780ac3",
+ "id": "9d7003f8",
"metadata": {
"lines_to_next_cell": 0,
"tags": []
@@ -910,7 +910,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "e7187b29",
+ "id": "f3b60479",
"metadata": {},
"outputs": [],
"source": [
@@ -934,7 +934,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "78521f46",
+ "id": "103b94b0",
"metadata": {
"lines_to_next_cell": 2
},
@@ -946,7 +946,7 @@
},
{
"cell_type": "markdown",
- "id": "036e6086",
+ "id": "d146e4f8",
"metadata": {
"lines_to_next_cell": 0,
"tags": []
@@ -968,7 +968,7 @@
},
{
"cell_type": "markdown",
- "id": "3b756b7a",
+ "id": "11e0f5dd",
"metadata": {
"lines_to_next_cell": 0,
"tags": []
@@ -980,7 +980,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "20847a1b",
+ "id": "79722273",
"metadata": {
"lines_to_next_cell": 0,
"tags": [
@@ -1091,7 +1091,7 @@
},
{
"cell_type": "markdown",
- "id": "78403aaa",
+ "id": "5a0870e3",
"metadata": {
"lines_to_next_cell": 0,
"tags": []
@@ -1103,7 +1103,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "9bb6c797",
+ "id": "9c9a471f",
"metadata": {},
"outputs": [],
"source": [
@@ -1119,7 +1119,7 @@
},
{
"cell_type": "markdown",
- "id": "c32cbd8b",
+ "id": "f01e0c51",
"metadata": {
"tags": []
},
@@ -1134,7 +1134,7 @@
},
{
"cell_type": "markdown",
- "id": "4c86dd42",
+ "id": "3c545933",
"metadata": {
"lines_to_next_cell": 0,
"tags": []
@@ -1146,7 +1146,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "8f728ded",
+ "id": "74225676",
"metadata": {},
"outputs": [],
"source": [
@@ -1168,7 +1168,7 @@
},
{
"cell_type": "markdown",
- "id": "028d3bbc",
+ "id": "b83dfcd2",
"metadata": {
"tags": []
},
@@ -1184,7 +1184,7 @@
},
{
"cell_type": "markdown",
- "id": "b63aac86",
+ "id": "740be1a4",
"metadata": {
"tags": []
},
@@ -1194,7 +1194,7 @@
},
{
"cell_type": "markdown",
- "id": "b0ad5935",
+ "id": "2a44a05e",
"metadata": {
"tags": []
},
@@ -1211,7 +1211,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "0cf2b9a5",
+ "id": "8d711fbe",
"metadata": {
"title": "Loading the test dataset"
},
@@ -1231,7 +1231,7 @@
},
{
"cell_type": "markdown",
- "id": "35cc9b35",
+ "id": "7c1d56b5",
"metadata": {
"lines_to_next_cell": 0,
"tags": []
@@ -1243,7 +1243,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "4146969c",
+ "id": "f649373f",
"metadata": {},
"outputs": [],
"source": [
@@ -1256,7 +1256,7 @@
},
{
"cell_type": "markdown",
- "id": "f99f676c",
+ "id": "4a3c2e42",
"metadata": {
"lines_to_next_cell": 0
},
@@ -1266,7 +1266,7 @@
},
{
"cell_type": "markdown",
- "id": "a7450339",
+ "id": "746827ec",
"metadata": {
"lines_to_next_cell": 0
},
@@ -1284,7 +1284,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "58973345",
+ "id": "855b63d4",
"metadata": {
"lines_to_next_cell": 0,
"tags": [
@@ -1320,7 +1320,7 @@
},
{
"cell_type": "markdown",
- "id": "20af6915",
+ "id": "9e21d254",
"metadata": {
"lines_to_next_cell": 0,
"tags": []
@@ -1332,7 +1332,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "4543762f",
+ "id": "143cb6c6",
"metadata": {},
"outputs": [],
"source": [
@@ -1345,7 +1345,7 @@
},
{
"cell_type": "markdown",
- "id": "d0b8a2ec",
+ "id": "a15cdb80",
"metadata": {
"tags": []
},
@@ -1360,7 +1360,7 @@
},
{
"cell_type": "markdown",
- "id": "61e58d7f",
+ "id": "2d2ced5b",
"metadata": {
"tags": []
},
@@ -1371,7 +1371,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "b8dc4640",
+ "id": "24639718",
"metadata": {},
"outputs": [],
"source": [
@@ -1385,7 +1385,7 @@
},
{
"cell_type": "markdown",
- "id": "ed9b7104",
+ "id": "8afab4b7",
"metadata": {
"tags": []
},
@@ -1400,7 +1400,7 @@
},
{
"cell_type": "markdown",
- "id": "0add70ab",
+ "id": "927a2361",
"metadata": {
"lines_to_next_cell": 0
},
@@ -1415,7 +1415,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "274d8226",
+ "id": "87aaa903",
"metadata": {},
"outputs": [],
"source": [
@@ -1436,7 +1436,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "b6b54bbe",
+ "id": "3633b841",
"metadata": {
"title": "Another visualization function"
},
@@ -1465,7 +1465,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "979ca20f",
+ "id": "32f5d3ba",
"metadata": {
"lines_to_next_cell": 0
},
@@ -1481,7 +1481,7 @@
},
{
"cell_type": "markdown",
- "id": "b779b535",
+ "id": "89ecd3a9",
"metadata": {
"lines_to_next_cell": 0
},
@@ -1497,7 +1497,7 @@
},
{
"cell_type": "markdown",
- "id": "c44f0cf1",
+ "id": "19612f27",
"metadata": {
"lines_to_next_cell": 0
},
@@ -1512,7 +1512,7 @@
},
{
"cell_type": "markdown",
- "id": "f402bb74",
+ "id": "f63764f2",
"metadata": {
"lines_to_next_cell": 0
},
@@ -1526,7 +1526,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "12542a6d",
+ "id": "1bcaa03b",
"metadata": {
"lines_to_next_cell": 0
},
@@ -1546,7 +1546,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "8d3e6d86",
+ "id": "d3b3324a",
"metadata": {
"lines_to_next_cell": 0
},
@@ -1582,7 +1582,7 @@
},
{
"cell_type": "markdown",
- "id": "ca1d1242",
+ "id": "81ea3fdd",
"metadata": {
"lines_to_next_cell": 0
},
@@ -1596,7 +1596,7 @@
},
{
"cell_type": "markdown",
- "id": "6f530e82",
+ "id": "92c0dba0",
"metadata": {
"lines_to_next_cell": 0
},
@@ -1612,7 +1612,7 @@
},
{
"cell_type": "markdown",
- "id": "5904b20b",
+ "id": "93ad40a6",
"metadata": {
"lines_to_next_cell": 0
},
@@ -1628,7 +1628,7 @@
},
{
"cell_type": "markdown",
- "id": "72ca6d87",
+ "id": "884f4f82",
"metadata": {
"lines_to_next_cell": 0
},
@@ -1651,7 +1651,7 @@
},
{
"cell_type": "markdown",
- "id": "a0baa037",
+ "id": "344c70a0",
"metadata": {},
"source": [
"
Task 5.1: Explore the style space
\n",
@@ -1663,7 +1663,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "bc0062db",
+ "id": "bc06e146",
"metadata": {},
"outputs": [],
"source": [
@@ -1698,7 +1698,7 @@
},
{
"cell_type": "markdown",
- "id": "ba428131",
+ "id": "518c6ddb",
"metadata": {
"lines_to_next_cell": 0
},
@@ -1714,7 +1714,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "2ee2e061",
+ "id": "40fa1f61",
"metadata": {
"lines_to_next_cell": 0
},
@@ -1741,7 +1741,7 @@
},
{
"cell_type": "markdown",
- "id": "a26903b8",
+ "id": "a204c00f",
"metadata": {
"lines_to_next_cell": 0
},
@@ -1755,7 +1755,7 @@
},
{
"cell_type": "markdown",
- "id": "7f72dfb5",
+ "id": "16971e9c",
"metadata": {
"lines_to_next_cell": 0
},
@@ -1772,7 +1772,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "be62a09b",
+ "id": "5d04746b",
"metadata": {},
"outputs": [],
"source": [
@@ -1794,7 +1794,7 @@
},
{
"cell_type": "markdown",
- "id": "f16385e4",
+ "id": "7dd5245c",
"metadata": {},
"source": [
"
Questions
\n",
@@ -1806,7 +1806,7 @@
},
{
"cell_type": "markdown",
- "id": "e0f59eee",
+ "id": "4ab3793f",
"metadata": {},
"source": [
"
Checkpoint 5
\n",
@@ -1824,7 +1824,7 @@
},
{
"cell_type": "markdown",
- "id": "0bbc6cd2",
+ "id": "2d4e3c2a",
"metadata": {},
"source": [
"# Bonus!\n",
@@ -1834,46 +1834,7 @@
"
What happens if you don't use the EMA model? \n",
"
What happens if you change the learning rates? \n",
"
What happens if you add a Sigmoid activation to the output of the style encoder? \n",
- "See what else you can think of, and see how finnicky training a GAN can be!\n",
- "\n",
- "# %% [markdown] tags=[\"solution\"]\n",
- "The colors for the classes are sampled from matplotlib colormaps! They are the four seasons: spring, summer, autumn, and winter.\n",
- "Check your style space again to see if you can see the patterns now!\n",
- "\n",
- "# %% tags=[\"solution\"]\n",
- "Let's plot the colormaps\n",
- "import matplotlib as mpl\n",
- "import numpy as np\n",
- "\n",
- "\n",
- "def plot_color_gradients(cmap_list):\n",
- " gradient = np.linspace(0, 1, 256)\n",
- " gradient = np.vstack((gradient, gradient))\n",
- "\n",
- " # Create figure and adjust figure height to number of colormaps\n",
- " nrows = len(cmap_list)\n",
- " figh = 0.35 + 0.15 + (nrows + (nrows - 1) * 0.1) * 0.22\n",
- " fig, axs = plt.subplots(nrows=nrows + 1, figsize=(6.4, figh))\n",
- " fig.subplots_adjust(top=1 - 0.35 / figh, bottom=0.15 / figh, left=0.2, right=0.99)\n",
- "\n",
- " for ax, name in zip(axs, cmap_list):\n",
- " ax.imshow(gradient, aspect=\"auto\", cmap=mpl.colormaps[name])\n",
- " ax.text(\n",
- " -0.01,\n",
- " 0.5,\n",
- " name,\n",
- " va=\"center\",\n",
- " ha=\"right\",\n",
- " fontsize=10,\n",
- " transform=ax.transAxes,\n",
- " )\n",
- "\n",
- " # Turn off *all* ticks & spines, not just the ones with colormaps.\n",
- " for ax in axs:\n",
- " ax.set_axis_off()\n",
- "\n",
- "\n",
- "plot_color_gradients([\"spring\", \"summer\", \"autumn\", \"winter\"])"
+ "See what else you can think of, and see how finnicky training a GAN can be!"
]
}
],
diff --git a/solution.ipynb b/solution.ipynb
index d4808b6..2fbb96f 100644
--- a/solution.ipynb
+++ b/solution.ipynb
@@ -2,7 +2,7 @@
"cells": [
{
"cell_type": "markdown",
- "id": "be4e7a97",
+ "id": "5836c5fd",
"metadata": {
"lines_to_next_cell": 0,
"tags": []
@@ -29,7 +29,7 @@
},
{
"cell_type": "markdown",
- "id": "a1e6c3cd",
+ "id": "c7ee63fa",
"metadata": {
"lines_to_next_cell": 0
},
@@ -41,7 +41,7 @@
},
{
"cell_type": "markdown",
- "id": "bc9d8f39",
+ "id": "25948d26",
"metadata": {},
"source": [
"\n",
@@ -54,7 +54,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "5a28affe",
+ "id": "8b8c18b6",
"metadata": {
"lines_to_next_cell": 0
},
@@ -68,7 +68,7 @@
},
{
"cell_type": "markdown",
- "id": "3fb92e01",
+ "id": "2d9a1fa2",
"metadata": {
"lines_to_next_cell": 0
},
@@ -84,7 +84,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "225052d7",
+ "id": "33bedaea",
"metadata": {},
"outputs": [],
"source": [
@@ -102,7 +102,7 @@
},
{
"cell_type": "markdown",
- "id": "a878ce13",
+ "id": "d8c857dc",
"metadata": {
"lines_to_next_cell": 0
},
@@ -113,7 +113,7 @@
},
{
"cell_type": "markdown",
- "id": "1f8d5401",
+ "id": "04aa9880",
"metadata": {
"lines_to_next_cell": 0
},
@@ -130,7 +130,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "dc1f9832",
+ "id": "c15b2288",
"metadata": {
"tags": [
"solution"
@@ -154,7 +154,7 @@
},
{
"cell_type": "markdown",
- "id": "6dd3913c",
+ "id": "252e596c",
"metadata": {
"lines_to_next_cell": 0
},
@@ -165,7 +165,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "060a05f5",
+ "id": "2bb3f66f",
"metadata": {
"lines_to_next_cell": 0
},
@@ -194,7 +194,7 @@
},
{
"cell_type": "markdown",
- "id": "2616d093",
+ "id": "ad6e8d02",
"metadata": {
"lines_to_next_cell": 0
},
@@ -211,7 +211,7 @@
},
{
"cell_type": "markdown",
- "id": "76fae027",
+ "id": "8ff2253c",
"metadata": {},
"source": [
"# Part 2: Using Integrated Gradients to find what the classifier knows\n",
@@ -221,7 +221,7 @@
},
{
"cell_type": "markdown",
- "id": "5284eaf7",
+ "id": "137f5e29",
"metadata": {},
"source": [
"## Attributions through integrated gradients\n",
@@ -234,7 +234,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "57eb7e30",
+ "id": "877b0dc5",
"metadata": {
"tags": []
},
@@ -252,7 +252,7 @@
},
{
"cell_type": "markdown",
- "id": "5dd749a7",
+ "id": "346433e9",
"metadata": {
"tags": []
},
@@ -268,7 +268,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "9e77b469",
+ "id": "e5cd638a",
"metadata": {
"tags": [
"solution"
@@ -292,7 +292,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "f1942f36",
+ "id": "d182aa7a",
"metadata": {
"tags": []
},
@@ -305,7 +305,7 @@
},
{
"cell_type": "markdown",
- "id": "7e5d1815",
+ "id": "ef1e380d",
"metadata": {
"lines_to_next_cell": 2,
"tags": []
@@ -317,7 +317,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "d5103ffb",
+ "id": "3fce7d60",
"metadata": {
"tags": []
},
@@ -345,7 +345,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "858a7c14",
+ "id": "d38da2c2",
"metadata": {
"tags": []
},
@@ -358,7 +358,7 @@
},
{
"cell_type": "markdown",
- "id": "78c186ef",
+ "id": "aff26564",
"metadata": {
"lines_to_next_cell": 2
},
@@ -372,7 +372,7 @@
},
{
"cell_type": "markdown",
- "id": "5e3aa105",
+ "id": "53ffc390",
"metadata": {
"lines_to_next_cell": 0
},
@@ -385,7 +385,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "8171ef5a",
+ "id": "160b27d5",
"metadata": {},
"outputs": [],
"source": [
@@ -410,7 +410,7 @@
},
{
"cell_type": "markdown",
- "id": "0b65a750",
+ "id": "42462cab",
"metadata": {
"lines_to_next_cell": 0
},
@@ -424,7 +424,7 @@
},
{
"cell_type": "markdown",
- "id": "06d9fccd",
+ "id": "b4cd9eac",
"metadata": {},
"source": [
"\n",
@@ -450,7 +450,7 @@
},
{
"cell_type": "markdown",
- "id": "1cf3195f",
+ "id": "dc603cd7",
"metadata": {},
"source": [
"
Task 2.3: Use random noise as a baseline
\n",
@@ -462,7 +462,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "b09d2144",
+ "id": "768a9e3b",
"metadata": {
"tags": [
"solution"
@@ -488,7 +488,7 @@
},
{
"cell_type": "markdown",
- "id": "e31bd3cf",
+ "id": "52c0979f",
"metadata": {
"tags": []
},
@@ -502,7 +502,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "af1e6318",
+ "id": "38a82581",
"metadata": {
"tags": [
"solution"
@@ -532,7 +532,7 @@
},
{
"cell_type": "markdown",
- "id": "290bdbf3",
+ "id": "30b56566",
"metadata": {
"tags": []
},
@@ -548,7 +548,7 @@
},
{
"cell_type": "markdown",
- "id": "659c5758",
+ "id": "ee7c164c",
"metadata": {},
"source": [
"
BONUS Task: Using different attributions.
\n",
@@ -562,7 +562,7 @@
},
{
"cell_type": "markdown",
- "id": "b93071a2",
+ "id": "71b2e6fa",
"metadata": {},
"source": [
"
Checkpoint 2
\n",
@@ -582,7 +582,7 @@
},
{
"cell_type": "markdown",
- "id": "e9f2b7ae",
+ "id": "e0966908",
"metadata": {
"lines_to_next_cell": 0
},
@@ -610,7 +610,7 @@
},
{
"cell_type": "markdown",
- "id": "92223fdc",
+ "id": "50bfe53d",
"metadata": {
"lines_to_next_cell": 0,
"tags": []
@@ -633,7 +633,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "5a72db0b",
+ "id": "b1ab5f6d",
"metadata": {},
"outputs": [],
"source": [
@@ -665,7 +665,7 @@
},
{
"cell_type": "markdown",
- "id": "01335c40",
+ "id": "7029ce21",
"metadata": {
"lines_to_next_cell": 0
},
@@ -680,7 +680,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "d86d3dcc",
+ "id": "8e83c444",
"metadata": {
"tags": [
"solution"
@@ -697,7 +697,7 @@
},
{
"cell_type": "markdown",
- "id": "186f40a5",
+ "id": "156d8774",
"metadata": {
"tags": []
},
@@ -712,7 +712,7 @@
},
{
"cell_type": "markdown",
- "id": "af4cf127",
+ "id": "48a541a1",
"metadata": {
"lines_to_next_cell": 0,
"tags": []
@@ -729,7 +729,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "1f145891",
+ "id": "1608ecf2",
"metadata": {
"lines_to_next_cell": 0,
"tags": [
@@ -743,7 +743,7 @@
},
{
"cell_type": "markdown",
- "id": "c2a072a4",
+ "id": "b16b319e",
"metadata": {
"lines_to_next_cell": 0
},
@@ -754,7 +754,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "f7bb217b",
+ "id": "1e85b7b2",
"metadata": {},
"outputs": [],
"source": [
@@ -764,7 +764,7 @@
},
{
"cell_type": "markdown",
- "id": "dfdd1272",
+ "id": "dc1c55cf",
"metadata": {
"lines_to_next_cell": 0,
"tags": []
@@ -782,7 +782,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "7ddd581a",
+ "id": "33e0ea83",
"metadata": {
"lines_to_next_cell": 0
},
@@ -794,7 +794,7 @@
},
{
"cell_type": "markdown",
- "id": "2f7fe43c",
+ "id": "6bbe594d",
"metadata": {
"lines_to_next_cell": 0,
"tags": []
@@ -813,7 +813,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "f01095a7",
+ "id": "7b5f7065",
"metadata": {},
"outputs": [],
"source": [
@@ -822,7 +822,7 @@
},
{
"cell_type": "markdown",
- "id": "bad091aa",
+ "id": "c4886cf1",
"metadata": {
"lines_to_next_cell": 0,
"tags": []
@@ -838,7 +838,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "e49c55e0",
+ "id": "1f2d9558",
"metadata": {},
"outputs": [],
"source": [
@@ -847,7 +847,7 @@
},
{
"cell_type": "markdown",
- "id": "af990b9a",
+ "id": "6632b7c6",
"metadata": {
"lines_to_next_cell": 0,
"tags": []
@@ -859,7 +859,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "291f2062",
+ "id": "2b336a53",
"metadata": {},
"outputs": [],
"source": [
@@ -872,7 +872,7 @@
},
{
"cell_type": "markdown",
- "id": "919aea73",
+ "id": "b7c49115",
"metadata": {
"lines_to_next_cell": 0,
"tags": []
@@ -886,7 +886,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "26f2a9c1",
+ "id": "e076c809",
"metadata": {},
"outputs": [],
"source": [
@@ -898,7 +898,7 @@
},
{
"cell_type": "markdown",
- "id": "54780ac3",
+ "id": "9d7003f8",
"metadata": {
"lines_to_next_cell": 0,
"tags": []
@@ -918,7 +918,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "e7187b29",
+ "id": "f3b60479",
"metadata": {},
"outputs": [],
"source": [
@@ -942,7 +942,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "78521f46",
+ "id": "103b94b0",
"metadata": {
"lines_to_next_cell": 2
},
@@ -954,7 +954,7 @@
},
{
"cell_type": "markdown",
- "id": "036e6086",
+ "id": "d146e4f8",
"metadata": {
"lines_to_next_cell": 0,
"tags": []
@@ -976,7 +976,7 @@
},
{
"cell_type": "markdown",
- "id": "3b756b7a",
+ "id": "11e0f5dd",
"metadata": {
"lines_to_next_cell": 0,
"tags": []
@@ -988,7 +988,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "8256f4b5",
+ "id": "6fefc28d",
"metadata": {
"lines_to_next_cell": 2,
"tags": [
@@ -1058,7 +1058,7 @@
},
{
"cell_type": "markdown",
- "id": "78403aaa",
+ "id": "5a0870e3",
"metadata": {
"lines_to_next_cell": 0,
"tags": []
@@ -1070,7 +1070,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "9bb6c797",
+ "id": "9c9a471f",
"metadata": {},
"outputs": [],
"source": [
@@ -1086,7 +1086,7 @@
},
{
"cell_type": "markdown",
- "id": "c32cbd8b",
+ "id": "f01e0c51",
"metadata": {
"tags": []
},
@@ -1101,7 +1101,7 @@
},
{
"cell_type": "markdown",
- "id": "4c86dd42",
+ "id": "3c545933",
"metadata": {
"lines_to_next_cell": 0,
"tags": []
@@ -1113,7 +1113,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "8f728ded",
+ "id": "74225676",
"metadata": {},
"outputs": [],
"source": [
@@ -1135,7 +1135,7 @@
},
{
"cell_type": "markdown",
- "id": "028d3bbc",
+ "id": "b83dfcd2",
"metadata": {
"tags": []
},
@@ -1151,7 +1151,7 @@
},
{
"cell_type": "markdown",
- "id": "b63aac86",
+ "id": "740be1a4",
"metadata": {
"tags": []
},
@@ -1161,7 +1161,7 @@
},
{
"cell_type": "markdown",
- "id": "b0ad5935",
+ "id": "2a44a05e",
"metadata": {
"tags": []
},
@@ -1178,7 +1178,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "0cf2b9a5",
+ "id": "8d711fbe",
"metadata": {
"title": "Loading the test dataset"
},
@@ -1198,7 +1198,7 @@
},
{
"cell_type": "markdown",
- "id": "35cc9b35",
+ "id": "7c1d56b5",
"metadata": {
"lines_to_next_cell": 0,
"tags": []
@@ -1210,7 +1210,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "4146969c",
+ "id": "f649373f",
"metadata": {},
"outputs": [],
"source": [
@@ -1223,7 +1223,7 @@
},
{
"cell_type": "markdown",
- "id": "f99f676c",
+ "id": "4a3c2e42",
"metadata": {
"lines_to_next_cell": 0
},
@@ -1233,7 +1233,7 @@
},
{
"cell_type": "markdown",
- "id": "a7450339",
+ "id": "746827ec",
"metadata": {
"lines_to_next_cell": 0
},
@@ -1251,7 +1251,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "f2bfd025",
+ "id": "870dd94a",
"metadata": {
"tags": [
"solution"
@@ -1288,7 +1288,7 @@
},
{
"cell_type": "markdown",
- "id": "20af6915",
+ "id": "9e21d254",
"metadata": {
"lines_to_next_cell": 0,
"tags": []
@@ -1300,7 +1300,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "4543762f",
+ "id": "143cb6c6",
"metadata": {},
"outputs": [],
"source": [
@@ -1313,7 +1313,7 @@
},
{
"cell_type": "markdown",
- "id": "d0b8a2ec",
+ "id": "a15cdb80",
"metadata": {
"tags": []
},
@@ -1328,7 +1328,7 @@
},
{
"cell_type": "markdown",
- "id": "61e58d7f",
+ "id": "2d2ced5b",
"metadata": {
"tags": []
},
@@ -1339,7 +1339,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "b8dc4640",
+ "id": "24639718",
"metadata": {},
"outputs": [],
"source": [
@@ -1353,7 +1353,7 @@
},
{
"cell_type": "markdown",
- "id": "ed9b7104",
+ "id": "8afab4b7",
"metadata": {
"tags": []
},
@@ -1368,7 +1368,7 @@
},
{
"cell_type": "markdown",
- "id": "0add70ab",
+ "id": "927a2361",
"metadata": {
"lines_to_next_cell": 0
},
@@ -1383,7 +1383,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "274d8226",
+ "id": "87aaa903",
"metadata": {},
"outputs": [],
"source": [
@@ -1404,7 +1404,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "b6b54bbe",
+ "id": "3633b841",
"metadata": {
"title": "Another visualization function"
},
@@ -1433,7 +1433,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "979ca20f",
+ "id": "32f5d3ba",
"metadata": {
"lines_to_next_cell": 0
},
@@ -1449,7 +1449,7 @@
},
{
"cell_type": "markdown",
- "id": "b779b535",
+ "id": "89ecd3a9",
"metadata": {
"lines_to_next_cell": 0
},
@@ -1465,7 +1465,7 @@
},
{
"cell_type": "markdown",
- "id": "c44f0cf1",
+ "id": "19612f27",
"metadata": {
"lines_to_next_cell": 0
},
@@ -1480,7 +1480,7 @@
},
{
"cell_type": "markdown",
- "id": "f402bb74",
+ "id": "f63764f2",
"metadata": {
"lines_to_next_cell": 0
},
@@ -1494,7 +1494,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "12542a6d",
+ "id": "1bcaa03b",
"metadata": {
"lines_to_next_cell": 0
},
@@ -1514,7 +1514,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "8d3e6d86",
+ "id": "d3b3324a",
"metadata": {
"lines_to_next_cell": 0
},
@@ -1550,7 +1550,7 @@
},
{
"cell_type": "markdown",
- "id": "ca1d1242",
+ "id": "81ea3fdd",
"metadata": {
"lines_to_next_cell": 0
},
@@ -1564,7 +1564,7 @@
},
{
"cell_type": "markdown",
- "id": "6f530e82",
+ "id": "92c0dba0",
"metadata": {
"lines_to_next_cell": 0
},
@@ -1580,7 +1580,7 @@
},
{
"cell_type": "markdown",
- "id": "5904b20b",
+ "id": "93ad40a6",
"metadata": {
"lines_to_next_cell": 0
},
@@ -1596,7 +1596,7 @@
},
{
"cell_type": "markdown",
- "id": "72ca6d87",
+ "id": "884f4f82",
"metadata": {
"lines_to_next_cell": 0
},
@@ -1619,7 +1619,7 @@
},
{
"cell_type": "markdown",
- "id": "a0baa037",
+ "id": "344c70a0",
"metadata": {},
"source": [
"
Task 5.1: Explore the style space
\n",
@@ -1631,7 +1631,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "bc0062db",
+ "id": "bc06e146",
"metadata": {},
"outputs": [],
"source": [
@@ -1666,7 +1666,7 @@
},
{
"cell_type": "markdown",
- "id": "ba428131",
+ "id": "518c6ddb",
"metadata": {
"lines_to_next_cell": 0
},
@@ -1682,7 +1682,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "2ee2e061",
+ "id": "40fa1f61",
"metadata": {
"lines_to_next_cell": 0
},
@@ -1709,7 +1709,7 @@
},
{
"cell_type": "markdown",
- "id": "a26903b8",
+ "id": "a204c00f",
"metadata": {
"lines_to_next_cell": 0
},
@@ -1723,7 +1723,7 @@
},
{
"cell_type": "markdown",
- "id": "7f72dfb5",
+ "id": "16971e9c",
"metadata": {
"lines_to_next_cell": 0
},
@@ -1740,7 +1740,7 @@
{
"cell_type": "code",
"execution_count": null,
- "id": "be62a09b",
+ "id": "5d04746b",
"metadata": {},
"outputs": [],
"source": [
@@ -1762,7 +1762,7 @@
},
{
"cell_type": "markdown",
- "id": "f16385e4",
+ "id": "7dd5245c",
"metadata": {},
"source": [
"
Questions
\n",
@@ -1774,7 +1774,7 @@
},
{
"cell_type": "markdown",
- "id": "e0f59eee",
+ "id": "4ab3793f",
"metadata": {},
"source": [
"
Checkpoint 5
\n",
@@ -1792,7 +1792,7 @@
},
{
"cell_type": "markdown",
- "id": "0bbc6cd2",
+ "id": "2d4e3c2a",
"metadata": {},
"source": [
"# Bonus!\n",
@@ -1802,14 +1802,34 @@
" What happens if you don't use the EMA model? \n",
" What happens if you change the learning rates? \n",
" What happens if you add a Sigmoid activation to the output of the style encoder? \n",
- "See what else you can think of, and see how finnicky training a GAN can be!\n",
- "\n",
- "# %% [markdown] tags=[\"solution\"]\n",
+ "See what else you can think of, and see how finnicky training a GAN can be!"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "1cd1cd8b",
+ "metadata": {
+ "tags": [
+ "solution"
+ ]
+ },
+ "source": [
"The colors for the classes are sampled from matplotlib colormaps! They are the four seasons: spring, summer, autumn, and winter.\n",
- "Check your style space again to see if you can see the patterns now!\n",
- "\n",
- "# %% tags=[\"solution\"]\n",
- "Let's plot the colormaps\n",
+ "Check your style space again to see if you can see the patterns now!"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "9ef23fc4",
+ "metadata": {
+ "tags": [
+ "solution"
+ ]
+ },
+ "outputs": [],
+ "source": [
+ "# Let's plot the colormaps\n",
"import matplotlib as mpl\n",
"import numpy as np\n",
"\n",