Last active
February 25, 2024 18:10
-
-
Save dicer2000/1bbf305afbf80e67de05b4c94da0bdd3 to your computer and use it in GitHub Desktop.
vt_demo1.ipynb
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"nbformat": 4, | |
"nbformat_minor": 0, | |
"metadata": { | |
"colab": { | |
"provenance": [], | |
"authorship_tag": "ABX9TyNeCsnPp8IOIbD9f+GZ29R6", | |
"include_colab_link": true | |
}, | |
"kernelspec": { | |
"name": "python3", | |
"display_name": "Python 3" | |
}, | |
"language_info": { | |
"name": "python" | |
} | |
}, | |
"cells": [ | |
{ | |
"cell_type": "markdown", | |
"metadata": { | |
"id": "view-in-github", | |
"colab_type": "text" | |
}, | |
"source": [ | |
"<a href=\"https://colab.research.google.com/gist/dicer2000/1bbf305afbf80e67de05b4c94da0bdd3/fordemo_visiontransformerattention.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"source": [ | |
"# Transformer Demo 1\n", | |
"(c)2024 Brett Huffman" | |
], | |
"metadata": { | |
"id": "uuGbAfQJarpC" | |
} | |
}, | |
{ | |
"cell_type": "code", | |
"source": [ | |
"!pip install vit-keras\n", | |
"!pip install tensorflow_addons" | |
], | |
"metadata": { | |
"id": "OIq5Hht0OR6z" | |
}, | |
"execution_count": null, | |
"outputs": [] | |
}, | |
{ | |
"cell_type": "code", | |
"source": [ | |
"import numpy as np\n", | |
"import matplotlib.pyplot as plt\n", | |
"from vit_keras import vit, utils, visualize" | |
], | |
"metadata": { | |
"id": "YBx9IckXPd88" | |
}, | |
"execution_count": null, | |
"outputs": [] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": { | |
"id": "tazNa6fBOEWi" | |
}, | |
"outputs": [], | |
"source": [ | |
"from vit_keras import vit, utils\n", | |
"\n", | |
"image_size = 384\n", | |
"classes = utils.get_imagenet_classes()\n", | |
"model = vit.vit_b16(\n", | |
" image_size=image_size,\n", | |
" activation='sigmoid',\n", | |
" pretrained=True,\n", | |
" include_top=True,\n", | |
" pretrained_top=True\n", | |
")\n" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"source": [ | |
"url = \"https://www.southernliving.com/thmb/tXa6uF93OgesMpTj8UVX6HfMNZw=/750x0/filters:no_upscale():max_bytes(150000):strip_icc():format(webp)/GettyImages-185743593-2000-507c6c8883a44851885ea4fbc10a2c9e.jpg\"\n", | |
"#url = \"https://www.southernliving.com/thmb/gDSg2Aw5imKm_SA-WtEpMHvoNxI=/750x0/filters:no_upscale():max_bytes(150000):strip_icc():format(webp)/GettyImages-1176203433-2000-d65f1dbf87a24f5f9072f7fd50ab62dd.jpg\"\n", | |
"image = utils.read(url, image_size)\n", | |
"X = vit.preprocess_inputs(image).reshape(1, image_size, image_size, 3)\n", | |
"y = model.predict(X)\n" | |
], | |
"metadata": { | |
"id": "aX5yuGZBPmDB" | |
}, | |
"execution_count": null, | |
"outputs": [] | |
}, | |
{ | |
"cell_type": "code", | |
"source": [ | |
"# Show the image\n", | |
"image" | |
], | |
"metadata": { | |
"id": "6-A6u837PP2y" | |
}, | |
"execution_count": null, | |
"outputs": [] | |
}, | |
{ | |
"cell_type": "code", | |
"source": [ | |
"# Get the top prediction\n", | |
"print(classes[y[0].argmax()]) # Get the top prediction" | |
], | |
"metadata": { | |
"id": "T2sbk9f2bDy0" | |
}, | |
"execution_count": null, | |
"outputs": [] | |
}, | |
{ | |
"cell_type": "code", | |
"source": [ | |
"for l in y[0].argsort()[-5:][::-1]: #Top 5 classes\n", | |
" print(classes[l])" | |
], | |
"metadata": { | |
"id": "9OAwB0phT8sT" | |
}, | |
"execution_count": null, | |
"outputs": [] | |
}, | |
{ | |
"cell_type": "code", | |
"source": [ | |
"# Get the attention values\n", | |
"attention_map = visualize.attention_map(model=model, image=image)\n", | |
"\n", | |
"# Plot results\n", | |
"fig, (ax1, ax2) = plt.subplots(ncols=2, figsize=(100, 100))\n", | |
"ax1.axis('off')\n", | |
"ax2.axis('off')\n", | |
"ax1.set_title('Original')\n", | |
"ax2.set_title('Attention Map')\n", | |
"_ = ax1.imshow(image)\n", | |
"_ = ax2.imshow(attention_map)" | |
], | |
"metadata": { | |
"id": "d18jymNMQaqP" | |
}, | |
"execution_count": null, | |
"outputs": [] | |
} | |
] | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment