Join the “Zero to Data Analyst” Bootcamp. Limited seats.

A 20-week program covering 7 courses, 12 assignments, 4 real-world projects, and 12 months of career support.

In [1]:

`import torch`

In [2]:

```
t1 = torch.tensor(4.)
t1
```

Out[2]:

`tensor(4.)`

In [3]:

`t1.dtype`

Out[3]:

`torch.float32`

In [4]:

```
t2 = torch.tensor([1., 2, 3,4])
t2
```

Out[4]:

`tensor([1., 2., 3., 4.])`

In [5]:

`t2.dtype`

Out[5]:

`torch.float32`

In [6]:

```
t3 = torch.tensor([[5.,6], [7,8], [9,10]])
t3
```

Out[6]:

```
tensor([[ 5., 6.],
[ 7., 8.],
[ 9., 10.]])
```

In [7]:

```
t4 = torch.tensor([
[
[11,12,13],
[13,14,15]
],
[
[15,16,17],
[17,18,19.]
]
])
t4
```

Out[7]:

```
tensor([[[11., 12., 13.],
[13., 14., 15.]],
[[15., 16., 17.],
[17., 18., 19.]]])
```

In [8]:

`t1.shape`

Out[8]:

`torch.Size([])`

In [9]:

`t2.shape`

Out[9]:

`torch.Size([4])`

In [10]:

`t3.shape`

Out[10]:

`torch.Size([3, 2])`

In [11]:

`t4.shape`

Out[11]:

`torch.Size([2, 2, 3])`

In [13]:

```
x = torch.tensor(3.)
w = torch.tensor(4., requires_grad = True)
b = torch.tensor(5., requires_grad = True)
```

In [14]:

```
y = w * x + b
y
```

Out[14]:

`tensor(17., grad_fn=<AddBackward0>)`

In [15]:

`y.backward()`

In [16]:

```
# Display gradiesnts.
print('dy/dx: ', x.grad)
print('dy/dw: ', w.grad)
print('dy/db: ', b.grad)
```

```
dy/dx: None
dy/dw: tensor(3.)
dy/db: tensor(1.)
```

In [17]:

```
import numpy as np
x = np.array([
[1,2],
[3.,4]
])
x
```

Out[17]:

```
array([[1., 2.],
[3., 4.]])
```

In [18]:

`type(x)`

Out[18]:

`numpy.ndarray`

In [23]:

```
y = torch.from_numpy(x) # use the same memory, does not create a copy.
y
```

Out[23]:

```
tensor([[1., 2.],
[3., 4.]], dtype=torch.float64)
```

In [20]:

`type(y)`

Out[20]:

`torch.Tensor`

In [22]:

```
z = torch.tensor(x) # Creates a copy of the oringinal data, not using the same space.
z
```

Out[22]:

```
tensor([[1., 2.],
[3., 4.]], dtype=torch.float64)
```

In [24]:

`x.dtype, y.dtype`

Out[24]:

`(dtype('float64'), torch.float64)`

In [25]:

```
a = y.numpy()
a
```

Out[25]:

```
array([[1., 2.],
[3., 4.]])
```

In [26]:

`import jovian`

In [27]:

`jovian.commit()`

```
[jovian] Saving notebook..
```

```
[jovian] Creating a new notebook on https://jovian.ml/
[jovian] Please enter your API key ( from https://jovian.ml/ ):
```

```
API Key: ···························································································································································································································································································································
```

```
[jovian] Uploading notebook..
[jovian] Capturing environment..
[jovian] Committed successfully! https://jovian.ml/walid-gomaa/my-pytorch-basics
```

In [ ]:

` `