thon | |
from textwrap import wrap | |
import matplotlib.pyplot as plt | |
import numpy as np | |
def plot_images(images, captions): | |
plt.figure(figsize=(20, 20)) | |
for i in range(len(images)): | |
ax = plt.subplot(1, len(images), i + 1) | |
caption = captions[i] | |
caption = "\n".join(wrap(caption, 12)) | |
plt.title(caption) | |
plt.imshow(images[i]) | |
plt.axis("off") | |
sample_images_to_visualize = [np.array(train_ds[i]["image"]) for i in range(5)] | |
sample_captions = [train_ds[i]["text"] for i in range(5)] | |
plot_images(sample_images_to_visualize, sample_captions) | |
Preprocess the dataset | |
Since the dataset has two modalities (image and text), the pre-processing pipeline will preprocess images and the captions. |