[Python] How do I train an object detection model using Torchvision's pre-trained models?

I read the torchvision API documentation using pre-trained models for object detection. This is an example they have included:

from torchvision.io.image import decode_image
from torchvision.models.detection import fasterrcnn_resnet50_fpn_v2, FasterRCNN_ResNet50_FPN_V2_Weights
from torchvision.utils import draw_bounding_boxes
from torchvision.transforms.functional import to_pil_image

img = decode_image("test/assets/encode_jpeg/grace_hopper_517x606.jpg")

# Step 1: Initialize model with the best available weights
weights = FasterRCNN_ResNet50_FPN_V2_Weights.DEFAULT
model = fasterrcnn_resnet50_fpn_v2(weights=weights, box_score_thresh=0.9)
model.eval()

# Step 2: Initialize the inference transforms
preprocess = weights.transforms()

# Step 3: Apply inference preprocessing transforms
batch = [preprocess(img)]

# Step 4: Use the model and visualize the prediction
prediction = model(batch)[0]
labels = [weights.meta["categories"] for i in prediction["labels"]]
box = draw_bounding_boxes(img, boxes=prediction["boxes"],
labels=labels,
colors="red",
width=4, font_size=30)
im = to_pil_image(box.detach())
im.show()


Based on this line:

img = decode_image("test/assets/encode_jpeg/grace_hopper_517x606.jpg")


the model is using only one image. Is there a way I can customize this so that I can train this model on several images?

Continue reading...