diff --git a/lecture1/exercise_0_python.ipynb b/lecture1/exercise_0_python.ipynb
index 5fbf96d4a221fbbbecbe4d1862c1c2e95075b937..ce05d5e82495d7d3d872f48f83d3e650272eb632 100644
--- a/lecture1/exercise_0_python.ipynb
+++ b/lecture1/exercise_0_python.ipynb
@@ -515,7 +515,7 @@
"metadata": {},
"source": [
"### Numpy One Dimensional Array Operations\n",
- "```numpy``` **operates** on arrays **element-wise** thus elementary operations are performed in an intuitive way."
+ "```numpy``` arrays can often be used in the same way as their low dimensional counterparts. ```numpy``` interally **boradcasts** the arrays to the correct shapes to perform operations with many values in a **vectorized manner** often making them very fast and resource efficient."
]
},
{
diff --git a/lecture1/exercise_0_pytorch.ipynb b/lecture1/exercise_0_pytorch.ipynb
index 069e474fb8d6cea4c12e5c11211f1464eddce0aa..e33b1297377c2aefa2668bb8ced05e63a88c592e 100644
--- a/lecture1/exercise_0_pytorch.ipynb
+++ b/lecture1/exercise_0_pytorch.ipynb
@@ -7,7 +7,7 @@
"source": [
"# PyTorch Tutorial\n",
"---------------\n",
- "Welcome to the pytorch tutorial! Here we will go through some of the basics of pytorch.\n",
+ "Welcome to the PyTorch tutorial! Here we will go through some of the basics of PyTorch.\n",
"\n",
"The library can be imported the as ```torch```:"
]
@@ -17,19 +17,7 @@
"execution_count": 1,
"id": "e812c4c3",
"metadata": {},
- "outputs": [
- {
- "ename": "ModuleNotFoundError",
- "evalue": "No module named 'torch'",
- "output_type": "error",
- "traceback": [
- "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
- "\u001b[0;31mModuleNotFoundError\u001b[0m Traceback (most recent call last)",
- "\u001b[0;32m/var/folders/dw/z8g0cw_s0nzcv0z1jn7vfgsm0000gn/T/ipykernel_1180/4265195184.py\u001b[0m in \u001b[0;36m<cell line: 1>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0;32mimport\u001b[0m \u001b[0mtorch\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
- "\u001b[0;31mModuleNotFoundError\u001b[0m: No module named 'torch'"
- ]
- }
- ],
+ "outputs": [],
"source": [
"import torch"
]
@@ -181,11 +169,11 @@
"\n",
"Normal Sample Properties:\n",
" Shape: torch.Size([1, 10000])\n",
- " Mean: tensor(0.9942)\n",
- " Std: tensor(0.5033)\n",
+ " Mean: tensor(1.0022)\n",
+ " Std: tensor(0.4985)\n",
"\n",
"The first row of the normal samples:\n",
- "tensor([0.6045, 0.4586, 0.8431, ..., 1.5992, 0.4570, 1.2081])\n"
+ "tensor([1.2843, 1.7621, 1.4764, ..., 1.1636, 0.1418, 0.9023])\n"
]
}
],
@@ -229,8 +217,8 @@
"\n",
"Uniform Sample Properties:\n",
" Shape: torch.Size([3, 100000])\n",
- " Mean: tensor([0.5000, 0.4996, 0.5005])\n",
- " Std: tensor([0.2893, 0.2885, 0.2884])\n"
+ " Mean: tensor([0.4984, 0.4998, 0.4998])\n",
+ " Std: tensor([0.2883, 0.2888, 0.2889])\n"
]
}
],
@@ -249,7 +237,7 @@
"metadata": {},
"source": [
"### Task <a class=\"tocSkip\">\n",
- "Implement the mean-square difference function in pytorch:\n",
+ "Implement the mean-square difference function in ```pytorch```:\n",
"$ L(x, y) = \\sum_i \\frac{(x_i-y_i)^2}{N}$"
]
},
@@ -260,11 +248,10 @@
"metadata": {},
"outputs": [
{
- "ename": "SyntaxError",
- "evalue": "invalid syntax (3637020795.py, line 10)",
- "output_type": "error",
- "traceback": [
- "\u001b[0;36m Input \u001b[0;32mIn [8]\u001b[0;36m\u001b[0m\n\u001b[0;31m print(loss(x,y))?\u001b[0m\n\u001b[0m ^\u001b[0m\n\u001b[0;31mSyntaxError\u001b[0m\u001b[0;31m:\u001b[0m invalid syntax\n"
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "0.0\n"
]
}
],
diff --git a/lecture1/exercise_0_tensorflow.ipynb b/lecture1/exercise_0_tensorflow.ipynb
index 8c3ec1f525c27943abdfd192656c00e7d262ad48..0e4511684313e0bced11f1e20667cc1bf99b92b8 100644
--- a/lecture1/exercise_0_tensorflow.ipynb
+++ b/lecture1/exercise_0_tensorflow.ipynb
@@ -5,17 +5,17 @@
"id": "269d507c",
"metadata": {},
"source": [
- "# Tensorflow Tutorial\n",
+ "# TensorFlow Tutorial\n",
"---------------------------------\n",
"\n",
- "Welcome to the Tesorflow tutorial! Here we are going to go through the most fundamental functions and the syntax of the library.\n",
+ "Welcome to the TensorFlow tutorial! Here we are going to go through the most fundamental functions and the syntax of the library.\n",
"\n",
- "Usually, tensorflow is imported as ``` tf```:"
+ "Usually, TensorFlow is imported as ``` tf```:"
]
},
{
"cell_type": "code",
- "execution_count": 4,
+ "execution_count": 1,
"id": "fb7e3964",
"metadata": {},
"outputs": [],
@@ -30,14 +30,14 @@
"metadata": {},
"source": [
"## Tensors\n",
- "One can create tensors in tensorflow using a **syntax similar to** that of **numpy**. These objects are considered to be constants by the library and hence **cannot be modified**; each operation on these objects returns a new tensor object.\n",
+ "One can create tensors in TensorFlow using a **syntax similar to** that of **numpy**. These objects are considered to be constants by the library and hence **cannot be modified**; each operation on these objects returns a new tensor object.\n",
"\n",
"You can find some examples of tensor creation below:"
]
},
{
"cell_type": "code",
- "execution_count": 5,
+ "execution_count": 2,
"id": "e776d989",
"metadata": {},
"outputs": [
@@ -51,11 +51,19 @@
" [1. 1.]\n",
" [1. 1.]], shape=(3, 2), dtype=float32)\n",
"tf.random_uniform([1, 3]) = tf.Tensor(\n",
- "[[0.6040745 0.5626584 0.02407873]\n",
- " [0.21266627 0.27840424 0.76470673]], shape=(2, 3), dtype=float32)\n",
+ "[[0.9423052 0.5366801 0.27889287]\n",
+ " [0.8005012 0.05723584 0.8107604 ]], shape=(2, 3), dtype=float32)\n",
"tf.linspace(1.0, 7.0, 4) = tf.Tensor([1. 3. 5. 7.], shape=(4,), dtype=float64)\n",
"tf.convert_to_tensor( np.linspace(1, 7, 4) ) = tf.Tensor([1. 3. 5. 7.], shape=(4,), dtype=float64)\n"
]
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "2022-08-08 09:54:22.810114: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: SSE4.1 SSE4.2 AVX AVX2 FMA\n",
+ "To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.\n"
+ ]
}
],
"source": [
@@ -66,11 +74,11 @@
"t5 = tf.convert_to_tensor(np.linspace(1, 7, 4))\n",
"\n",
"# Observe that all of these objects are tensors:\n",
- "print(\"tf.ones([3, 2]) = %s\" % t1)\n",
- "print(\"tf.zeros([5]) = %s\" % t2)\n",
- "print(\"tf.random_uniform([1, 3]) = %s\" % t3)\n",
- "print(\"tf.linspace(1.0, 7.0, 4) = %s\" % t4)\n",
- "print(\"tf.convert_to_tensor( np.linspace(1, 7, 4) ) = %s\" % t5)"
+ "print(\"tf.ones([3, 2]) =\", t1)\n",
+ "print(\"tf.zeros([5]) =\", t2)\n",
+ "print(\"tf.random_uniform([1, 3]) =\", t3)\n",
+ "print(\"tf.linspace(1.0, 7.0, 4) =\", t4)\n",
+ "print(\"tf.convert_to_tensor( np.linspace(1, 7, 4) ) =\", t5)"
]
},
{
@@ -83,7 +91,7 @@
},
{
"cell_type": "code",
- "execution_count": 6,
+ "execution_count": 3,
"id": "0b576f35",
"metadata": {},
"outputs": [
@@ -91,8 +99,8 @@
"name": "stdout",
"output_type": "stream",
"text": [
- "[[0.6040745 0.5626584 0.02407873]\n",
- " [0.21266627 0.27840424 0.76470673]]\n",
+ "[[0.9423052 0.5366801 0.27889287]\n",
+ " [0.8005012 0.05723584 0.8107604 ]]\n",
"<class 'numpy.ndarray'>\n"
]
}
@@ -108,12 +116,12 @@
"metadata": {},
"source": [
"## Variables\n",
- "On the other hand, ```Variables``` (based on tensors) are objects which are **updated during training** through backpropagation. Each tensorflow variable has to be initialized and their values can be changed using ```variable.assign(new_values)```:"
+ "On the other hand, ```Variables``` (based on tensors) are objects which are **updated during training** through backpropagation. Each TensorFlow variable has to be initialized and their values can be changed using ```variable.assign(new_values)```:"
]
},
{
"cell_type": "code",
- "execution_count": 7,
+ "execution_count": 4,
"id": "a70aa763",
"metadata": {},
"outputs": [
@@ -133,10 +141,10 @@
}
],
"source": [
- "w = tf.Variable(tf.zeros([3, 2])) # Create an empty variable w\n",
- "print(\"w = %s\" % w) # ...which has zeros only by default\n",
- "w.assign(tf.ones([3, 2])) # Assign new values to w\n",
- "print(\"w = %s\" % w) # ... and retrieve them"
+ "w = tf.Variable(tf.zeros([3, 2])) # Create an empty variable w\n",
+ "print(\"w =\", w) # ...which has zeros only by default\n",
+ "w.assign(tf.ones([3, 2])) # Assign new values to w\n",
+ "print(\"w =\", w) # ... and retrieve them"
]
},
{
@@ -152,7 +160,7 @@
},
{
"cell_type": "code",
- "execution_count": 8,
+ "execution_count": 5,
"id": "367e4ba0",
"metadata": {},
"outputs": [
@@ -161,10 +169,10 @@
"output_type": "stream",
"text": [
"x = tf.Tensor([0. 1. 2. 3. 4.], shape=(5,), dtype=float32)\n",
- "(x+1)**2 - 2) = tf.Tensor([-1. 2. 7. 14. 23.], shape=(5,), dtype=float32)\n",
- "sin(x) tf.Tensor([ 0. 0.84147096 0.9092974 0.14112 -0.7568025 ], shape=(5,), dtype=float32)\n",
- "sum(x) tf.Tensor(10.0, shape=(), dtype=float32)\n",
- "mean(x) tf.Tensor(2.0, shape=(), dtype=float32)\n"
+ "(x+1)**2 - 2 = tf.Tensor([-1. 2. 7. 14. 23.], shape=(5,), dtype=float32)\n",
+ "sin(x) = tf.Tensor([ 0. 0.84147096 0.9092974 0.14112 -0.7568025 ], shape=(5,), dtype=float32)\n",
+ "sum(x) = tf.Tensor(10.0, shape=(), dtype=float32)\n",
+ "mean(x) = tf.Tensor(2.0, shape=(), dtype=float32)\n"
]
}
],
@@ -172,15 +180,15 @@
"x = tf.linspace(0., 4., 5) # Create a tensor array\n",
"\n",
"print(\"x =\", x)\n",
- "print(\"(x+1)**2 - 2) =\", (x + 1.)**2 - 2.)\n",
- "print(\"sin(x)\", tf.sin(x))\n",
- "print(\"sum(x)\", tf.reduce_sum(x))\n",
- "print(\"mean(x)\", tf.reduce_mean(x))"
+ "print(\"(x+1)**2 - 2 =\", (x + 1.)**2 - 2.)\n",
+ "print(\"sin(x) =\", tf.sin(x))\n",
+ "print(\"sum(x) =\", tf.reduce_sum(x))\n",
+ "print(\"mean(x) =\", tf.reduce_mean(x))"
]
},
{
"cell_type": "code",
- "execution_count": 9,
+ "execution_count": 6,
"id": "58c8bd1d",
"metadata": {},
"outputs": [
@@ -192,7 +200,7 @@
" [0., 0., 0.]], dtype=float32)>"
]
},
- "execution_count": 9,
+ "execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
@@ -212,7 +220,7 @@
},
{
"cell_type": "code",
- "execution_count": 10,
+ "execution_count": 7,
"id": "dd02b475",
"metadata": {},
"outputs": [
@@ -220,8 +228,8 @@
"name": "stdout",
"output_type": "stream",
"text": [
- "Means: tf.Tensor([-0.00430035 -0.00648657 0.01164796], shape=(3,), dtype=float32)\n",
- "Stds: tf.Tensor([1.0067673 0.99281996 0.993856 ], shape=(3,), dtype=float32)\n"
+ "Means: tf.Tensor([-0.00242303 -0.00101589 -0.01899738], shape=(3,), dtype=float32)\n",
+ "Stds: tf.Tensor([0.99289805 1.0028254 1.00137 ], shape=(3,), dtype=float32)\n"
]
}
],
@@ -245,7 +253,7 @@
},
{
"cell_type": "code",
- "execution_count": 12,
+ "execution_count": 8,
"id": "d925efd7",
"metadata": {},
"outputs": [