| import os | |
| import tensorflow as tf | |
| import numpy as np | |
| import pandas as pd | |
| import matplotlib.pyplot as plt | |
| from tensorflow import keras | |
| import requests | |
| import PIL | |
| import io | |
| import matplotlib.pyplot as plt | |
| from keras_cv_attention_models import convnext | |
| import gradio as gr | |
| mm = convnext.ConvNeXtBase() | |
| def inference(img): | |
| img = img | |
| imm = keras.applications.imagenet_utils.preprocess_input(img, mode='torch') | |
| image_input = tf.expand_dims(tf.image.resize(imm, mm.input_shape[1:3]), 0) | |
| pred = mm(image_input) | |
| pred_np = pred.numpy() | |
| pred_names = keras.applications.imagenet_utils.decode_predictions(pred.numpy())[0] | |
| result = {} | |
| for i in range(5): | |
| result[pred_names[i][1]] = pred_names[i][2].item() | |
| return result | |
| inputs = gr.inputs.Image(type='numpy') | |
| outputs = gr.outputs.Label(type="confidences",num_top_classes=5) | |
| title = "ConvNeXt" | |
| description = "Gradio demo for ConvNeXt. To use it, simply upload your image, or click one of the examples to load them. Read more at the links below." | |
| article = "<p style='text-align: center'><a href='A ConvNet for the 2020s'>MobileNetV2: Inverted Residuals and Linear Bottlenecks</a> | <a href='https://github.com/facebookresearch/ConvNeXt'>Github Repo</a> | <a href='https://github.com/leondgarse/keras_cv_attention_models'>pretrained ConvNeXt model from keras_cv_attention_models</a></p>" | |
| gr.Interface(inference, inputs, outputs, title=title, description=description, article=article, analytics_enabled=False).launch() |