involution / app.py
ariG23498's picture
add: app and examples
547271a
from huggingface_hub import from_pretrained_keras
import tensorflow as tf
import gradio as gr
# download the model in the global context
vis_model = from_pretrained_keras("ariG23498/involution")
def infer(test_image):
# convert the image to a tensorflow tensor and resize the image
# to a constant 32x32
image = tf.constant(test_image)
image = tf.image.resize(image, (32, 32))
# Use the model and get the activation maps
(inv1_out, inv2_out, inv3_out) = vis_model.predict(image[None, ...])
_, inv1_kernel = inv1_out
_, inv2_kernel = inv2_out
_, inv3_kernel = inv3_out
inv1_kernel = tf.reduce_sum(inv1_kernel, axis=[-1, -2, -3])
inv2_kernel = tf.reduce_sum(inv2_kernel, axis=[-1, -2, -3])
inv3_kernel = tf.reduce_sum(inv3_kernel, axis=[-1, -2, -3])
return (
inv1_kernel[0, ..., None],
inv2_kernel[0, ..., None],
inv3_kernel[0, ..., None]
)
iface = gr.Interface(
fn=infer,
title = "Involutional Neural Networks",
description =
"""Authors: [Aritra Roy Gosthipaty](https://twitter.com/ariG23498) and [Ritwik Raha](https://twitter.com/ritwik_raha)
Paper: [Involution: Inverting the Inherence of Convolution for Visual Recognition](https://arxiv.org/abs/2103.06255)
""",
inputs=gr.inputs.Image(label="Input Image"),
outputs=[
gr.outputs.Image(label="Activation from Kernel 1"),
gr.outputs.Image(label="Activation from Kernel 2"),
gr.outputs.Image(label="Activation from Kernel 3"),
],
examples=[["examples/llama.jpeg"], ["examples/dalai-lamao.jpeg"]],
).launch()