Add pretrained models guide

[sarahsanders-docker]

Description

• Created guide on Loading Pretrained Models

Issue Solved

#5869

Type of Change

• Adding a new entry

Checklist

• All writings are my own.
• My entry follows the Codecademy Docs style guide.
• My changes generate no new warnings.
• I have performed a self-review of my own writing and code.
• I have checked my entry and corrected any misspellings.
• I have made corresponding changes to the documentation if needed.
• I have confirmed my changes are not being pushed from my forked main branch.
• I have confirmed that I'm pushing from a new branch named after the changes I'm making.
• I have linked any issues that are relevant to this PR in the Issues Solved section.

[CLAassistant]

All committers have signed the CLA.

[mamtawardhani]

Thank you for contributing to Codecademy Docs @sarahsanders 😄

The entry looks good for a second round of review 🚀

[mamtawardhani]

Suggested change

	Title: Loading Pretrained Models
	Description: 'A brief description.' # Required; ideally under 150 characters and starts with a noun (used in search engine results and content previews)
	Subjects:
	- Machine Learning
	Tags:
	- Machine Learning
	- Models
	- Neural Networks
	- Deep Learning
	- TensorFlow
	- PyTorch
	- Datasets
	- Scikit-learn
	- AI
	CatalogContent: # Please use course/path landing page slugs, rather than linking to individual content items. If listing multiple items, please put the most relevant one first
	- 'learn-example-course'
	- 'paths/example-path'
	Title: 'Loading Pre-trained Models'
	Description: 'Initializes a model architecture with pre-trained weights learned from a large dataset, enabling transfer learning or direct inference.'
	Subjects:
	- 'Machine Learning'
	Tags:
	- 'Machine Learning'
	- 'Models'
	- 'Neural Networks'
	- 'Deep Learning'
	- 'TensorFlow'
	- 'PyTorch'
	- 'Datasets'
	- 'Scikit-learn'
	- 'AI'
	CatalogContent:
	- 'learn-python-3'
	- 'paths/computer-science'

[mamtawardhani]

Suggested change

**Pretrained models** are a foundational concept in machine learning, allowing developers and researchers to leverage models that have already been trained on extensive datasets. This approach accelerates development and improves accuracy by transferring knowledge from existing solutions to new tasks. In PyTorch, loading pretrained models is straightforward and provides access to many state-of-the-art models via the torchvision library and other community-supported sources.

**Loading pre-trained models** is a foundational process in machine learning that enables developers and researchers to utilize models already trained on extensive datasets. This practice speeds development and enhances accuracy by reusing learned features from existing solutions for new tasks. In PyTorch, loading pre-trained models is simple and accessible, offering a range of state-of-the-art models through libraries like `torchvision` and other community-contributed sources.

[mamtawardhani]

Suggested change

	- `<model_name>`: Replace this with the desired model name (e.g., `resnet18`, `vgg16`).
	- `pretrained=True`: Specifies that the model should load pretrained weights.
	- `<model_name>`: The name of the model to load (e.g., `resnet18`, `vgg16`, `mobilenet_v2`, etc.). It must be a valid model name from the `torchvision.models` library.
	- `pretrained`: If `True`, the function loads a model initialized with weights pre-trained on the ImageNet dataset. If `False`, it loads a model with random weights.

[mamtawardhani]

Suggested change

	This example demonstrates loading a pretrained ResNet-18 model and using it for image classification.
	This example demonstrates how to load a pre-trained ResNet-18 model and use it for image classification:

[mamtawardhani]

Suggested change

	Here is an example of modifying a pretrained ResNet-18 model for a custom classification task:
	The following example shows how to modify a pre-trained ResNet-18 model for a custom classification task:

[mamtawardhani]

Suggested change

	```python
	```py

[mamtawardhani]

Suggested change

	import torch.nn as nn
	# Load pretrained model
	model = models.resnet18(pretrained=True)
	# Modify the final fully connected layer to match the number of output classes
	num_classes = 10 # Adjust based on your dataset
	model.fc = nn.Linear(model.fc.in_features, num_classes)
	# Define loss and optimizer
	criterion = nn.CrossEntropyLoss()
	optimizer = torch.optim.Adam(model.parameters(), lr=0.001)
	# The model is now ready for training on your dataset
	import torch.nn as nn
	from torchvision import models
	# Load the pretrained ResNet-18 model
	model = models.resnet18(pretrained=True)
	# Modify the final fully connected layer to match the number of output classes
	num_classes = 10 # Replace with the number of classes in your custom dataset
	model.fc = nn.Linear(model.fc.in_features, num_classes)
	# Define loss and optimizer
	criterion = nn.CrossEntropyLoss() # Loss function for classification
	optimizer = torch.optim.Adam(model.parameters(), lr=0.001) # Optimizer for training
	# The model is now ready for fine-tuning on your dataset