formatting

Author: davidADSP

docker/Dockerfile

@@ -3,7 +3,6 @@ FROM ubuntu:20.04
 ENV DEBIAN_FRONTEND noninteractive
 
 RUN apt-get update
-RUN apt-get -y upgrade
 RUN apt-get install -y unzip graphviz curl musescore3 python3-pip
 
 RUN pip install --upgrade pip

notebooks/02_deeplearning/01_mlp/mlp.ipynb

@@ -126,7 +126,9 @@
    "outputs": [],
    "source": [
     "opt = optimizers.Adam(learning_rate=0.0005)\n",
-    "model.compile(loss=\"categorical_crossentropy\", optimizer=opt, metrics=[\"accuracy\"])"
+    "model.compile(\n",
+    "    loss=\"categorical_crossentropy\", optimizer=opt, metrics=[\"accuracy\"]\n",
+    ")"
    ]
   },
   {
@@ -162,7 +164,20 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "CLASSES = np.array([\"airplane\", \"automobile\", \"bird\", \"cat\", \"deer\", \"dog\", \"frog\", \"horse\", \"ship\", \"truck\"])\n",
+    "CLASSES = np.array(\n",
+    "    [\n",
+    "        \"airplane\",\n",
+    "        \"automobile\",\n",
+    "        \"bird\",\n",
+    "        \"cat\",\n",
+    "        \"deer\",\n",
+    "        \"dog\",\n",
+    "        \"frog\",\n",
+    "        \"horse\",\n",
+    "        \"ship\",\n",
+    "        \"truck\",\n",
+    "    ]\n",
+    ")\n",
     "\n",
     "preds = model.predict(x_test)\n",
     "preds_single = CLASSES[np.argmax(preds, axis=-1)]\n",
@@ -187,8 +202,22 @@
     "    img = x_test[idx]\n",
     "    ax = fig.add_subplot(1, n_to_show, i + 1)\n",
     "    ax.axis(\"off\")\n",
-    "    ax.text(0.5, -0.35, \"pred = \" + str(preds_single[idx]), fontsize=10, ha=\"center\", transform=ax.transAxes)\n",
-    "    ax.text(0.5, -0.7, \"act = \" + str(actual_single[idx]), fontsize=10, ha=\"center\", transform=ax.transAxes)\n",
+    "    ax.text(\n",
+    "        0.5,\n",
+    "        -0.35,\n",
+    "        \"pred = \" + str(preds_single[idx]),\n",
+    "        fontsize=10,\n",
+    "        ha=\"center\",\n",
+    "        transform=ax.transAxes,\n",
+    "    )\n",
+    "    ax.text(\n",
+    "        0.5,\n",
+    "        -0.7,\n",
+    "        \"act = \" + str(actual_single[idx]),\n",
+    "        fontsize=10,\n",
+    "        ha=\"center\",\n",
+    "        transform=ax.transAxes,\n",
+    "    )\n",
     "    ax.imshow(img)"
    ]
   }

notebooks/02_deeplearning/02_cnn/cnn.ipynb

@@ -98,7 +98,9 @@
    "source": [
     "input_layer = layers.Input((32, 32, 3))\n",
     "\n",
-    "x = layers.Conv2D(filters=32, kernel_size=3, strides=1, padding=\"same\")(input_layer)\n",
+    "x = layers.Conv2D(filters=32, kernel_size=3, strides=1, padding=\"same\")(\n",
+    "    input_layer\n",
+    ")\n",
     "x = layers.BatchNormalization()(x)\n",
     "x = layers.LeakyReLU()(x)\n",
     "\n",
@@ -145,7 +147,9 @@
    "outputs": [],
    "source": [
     "opt = optimizers.Adam(learning_rate=0.0005)\n",
-    "model.compile(loss=\"categorical_crossentropy\", optimizer=opt, metrics=[\"accuracy\"])"
+    "model.compile(\n",
+    "    loss=\"categorical_crossentropy\", optimizer=opt, metrics=[\"accuracy\"]\n",
+    ")"
    ]
   },
   {
@@ -156,7 +160,14 @@
    },
    "outputs": [],
    "source": [
-    "model.fit(x_train, y_train, batch_size=32, epochs=10, shuffle=True, validation_data=(x_test, y_test))"
+    "model.fit(\n",
+    "    x_train,\n",
+    "    y_train,\n",
+    "    batch_size=32,\n",
+    "    epochs=10,\n",
+    "    shuffle=True,\n",
+    "    validation_data=(x_test, y_test),\n",
+    ")"
    ]
   },
   {
@@ -183,7 +194,20 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "CLASSES = np.array([\"airplane\", \"automobile\", \"bird\", \"cat\", \"deer\", \"dog\", \"frog\", \"horse\", \"ship\", \"truck\"])\n",
+    "CLASSES = np.array(\n",
+    "    [\n",
+    "        \"airplane\",\n",
+    "        \"automobile\",\n",
+    "        \"bird\",\n",
+    "        \"cat\",\n",
+    "        \"deer\",\n",
+    "        \"dog\",\n",
+    "        \"frog\",\n",
+    "        \"horse\",\n",
+    "        \"ship\",\n",
+    "        \"truck\",\n",
+    "    ]\n",
+    ")\n",
     "\n",
     "preds = model.predict(x_test)\n",
     "preds_single = CLASSES[np.argmax(preds, axis=-1)]\n",
@@ -208,8 +232,22 @@
     "    img = x_test[idx]\n",
     "    ax = fig.add_subplot(1, n_to_show, i + 1)\n",
     "    ax.axis(\"off\")\n",
-    "    ax.text(0.5, -0.35, \"pred = \" + str(preds_single[idx]), fontsize=10, ha=\"center\", transform=ax.transAxes)\n",
-    "    ax.text(0.5, -0.7, \"act = \" + str(actual_single[idx]), fontsize=10, ha=\"center\", transform=ax.transAxes)\n",
+    "    ax.text(\n",
+    "        0.5,\n",
+    "        -0.35,\n",
+    "        \"pred = \" + str(preds_single[idx]),\n",
+    "        fontsize=10,\n",
+    "        ha=\"center\",\n",
+    "        transform=ax.transAxes,\n",
+    "    )\n",
+    "    ax.text(\n",
+    "        0.5,\n",
+    "        -0.7,\n",
+    "        \"act = \" + str(actual_single[idx]),\n",
+    "        fontsize=10,\n",
+    "        ha=\"center\",\n",
+    "        transform=ax.transAxes,\n",
+    "    )\n",
     "    ax.imshow(img)"
    ]
   }

notebooks/03_vae/01_autoencoder/autoencoder.ipynb

@@ -131,8 +131,12 @@
    "outputs": [],
    "source": [
     "# Encoder\n",
-    "encoder_input = layers.Input(shape=(IMAGE_SIZE, IMAGE_SIZE, CHANNELS), name=\"encoder_input\")\n",
-    "x = layers.Conv2D(32, (3, 3), strides=2, activation=\"relu\", padding=\"same\")(encoder_input)\n",
+    "encoder_input = layers.Input(\n",
+    "    shape=(IMAGE_SIZE, IMAGE_SIZE, CHANNELS), name=\"encoder_input\"\n",
+    ")\n",
+    "x = layers.Conv2D(32, (3, 3), strides=2, activation=\"relu\", padding=\"same\")(\n",
+    "    encoder_input\n",
+    ")\n",
     "x = layers.Conv2D(64, (3, 3), strides=2, activation=\"relu\", padding=\"same\")(x)\n",
     "x = layers.Conv2D(128, (3, 3), strides=2, activation=\"relu\", padding=\"same\")(x)\n",
     "shape_before_flattening = K.int_shape(x)[1:]  # the decoder will need this!\n",
@@ -155,11 +159,22 @@
     "decoder_input = layers.Input(shape=(EMBEDDING_DIM,), name=\"decoder_input\")\n",
     "x = layers.Dense(np.prod(shape_before_flattening))(decoder_input)\n",
     "x = layers.Reshape(shape_before_flattening)(x)\n",
-    "x = layers.Conv2DTranspose(128, (3, 3), strides=2, activation=\"relu\", padding=\"same\")(x)\n",
-    "x = layers.Conv2DTranspose(64, (3, 3), strides=2, activation=\"relu\", padding=\"same\")(x)\n",
-    "x = layers.Conv2DTranspose(32, (3, 3), strides=2, activation=\"relu\", padding=\"same\")(x)\n",
+    "x = layers.Conv2DTranspose(\n",
+    "    128, (3, 3), strides=2, activation=\"relu\", padding=\"same\"\n",
+    ")(x)\n",
+    "x = layers.Conv2DTranspose(\n",
+    "    64, (3, 3), strides=2, activation=\"relu\", padding=\"same\"\n",
+    ")(x)\n",
+    "x = layers.Conv2DTranspose(\n",
+    "    32, (3, 3), strides=2, activation=\"relu\", padding=\"same\"\n",
+    ")(x)\n",
     "decoder_output = layers.Conv2D(\n",
-    "    CHANNELS, (3, 3), strides=1, activation=\"sigmoid\", padding=\"same\", name=\"decoder_output\"\n",
+    "    CHANNELS,\n",
+    "    (3, 3),\n",
+    "    strides=1,\n",
+    "    activation=\"sigmoid\",\n",
+    "    padding=\"same\",\n",
+    "    name=\"decoder_output\",\n",
     ")(x)\n",
     "\n",
     "decoder = models.Model(decoder_input, decoder_output)\n",
@@ -174,7 +189,9 @@
    "outputs": [],
    "source": [
     "# Autoencoder\n",
-    "autoencoder = models.Model(encoder_input, decoder(encoder_output))  # decoder(encoder_output)\n",
+    "autoencoder = models.Model(\n",
+    "    encoder_input, decoder(encoder_output)\n",
+    ")  # decoder(encoder_output)\n",
     "autoencoder.summary()"
    ]
   },
@@ -344,7 +361,14 @@
     "\n",
     "figsize = 8\n",
     "plt.figure(figsize=(figsize, figsize))\n",
-    "plt.scatter(embeddings[:, 0], embeddings[:, 1], cmap=\"rainbow\", c=example_labels, alpha=0.8, s=3)\n",
+    "plt.scatter(\n",
+    "    embeddings[:, 0],\n",
+    "    embeddings[:, 1],\n",
+    "    cmap=\"rainbow\",\n",
+    "    c=example_labels,\n",
+    "    alpha=0.8,\n",
+    "    s=3,\n",
+    ")\n",
     "plt.colorbar()\n",
     "plt.show()"
    ]
@@ -369,7 +393,9 @@
     "\n",
     "# Sample some points in the latent space\n",
     "grid_width, grid_height = (6, 3)\n",
-    "sample = np.random.uniform(mins, maxs, size=(grid_width * grid_height, EMBEDDING_DIM))"
+    "sample = np.random.uniform(\n",
+    "    mins, maxs, size=(grid_width * grid_height, EMBEDDING_DIM)\n",
+    ")"
    ]
   },
   {
@@ -408,7 +434,14 @@
     "for i in range(grid_width * grid_height):\n",
     "    ax = fig.add_subplot(grid_height, grid_width, i + 1)\n",
     "    ax.axis(\"off\")\n",
-    "    ax.text(0.5, -0.35, str(np.round(sample[i, :], 1)), fontsize=10, ha=\"center\", transform=ax.transAxes)\n",
+    "    ax.text(\n",
+    "        0.5,\n",
+    "        -0.35,\n",
+    "        str(np.round(sample[i, :], 1)),\n",
+    "        fontsize=10,\n",
+    "        ha=\"center\",\n",
+    "        transform=ax.transAxes,\n",
+    "    )\n",
     "    ax.imshow(reconstructions[i, :, :], cmap=\"Greys\")"
    ]
   },
@@ -423,7 +456,14 @@
     "figsize = 12\n",
     "grid_size = 15\n",
     "plt.figure(figsize=(figsize, figsize))\n",
-    "plt.scatter(embeddings[:, 0], embeddings[:, 1], cmap=\"rainbow\", c=example_labels, alpha=0.8, s=300)\n",
+    "plt.scatter(\n",
+    "    embeddings[:, 0],\n",
+    "    embeddings[:, 1],\n",
+    "    cmap=\"rainbow\",\n",
+    "    c=example_labels,\n",
+    "    alpha=0.8,\n",
+    "    s=300,\n",
+    ")\n",
     "plt.colorbar()\n",
     "\n",
     "x = np.linspace(min(embeddings[:, 0]), max(embeddings[:, 0]), grid_size)\n",