inception_v3 / app.py
akhaliq's picture
akhaliq HF staff
Update app.py
7348f33
import tensorflow as tf
import tensorflow_hub as hub
import requests
from PIL import Image
from io import BytesIO
import matplotlib.pyplot as plt
import numpy as np
import gradio as gr
#@title Helper functions for loading image (hidden)
original_image_cache = {}
def preprocess_image(image):
image = np.array(image)
# reshape into shape [batch_size, height, width, num_channels]
img_reshaped = tf.reshape(image, [1, image.shape[0], image.shape[1], image.shape[2]])
# Use `convert_image_dtype` to convert to floats in the [0,1] range.
image = tf.image.convert_image_dtype(img_reshaped, tf.float32)
return image
def load_image_from_url(img_url):
"""Returns an image with shape [1, height, width, num_channels]."""
user_agent = {'User-agent': 'Colab Sample (https://tensorflow.org)'}
response = requests.get(img_url, headers=user_agent)
image = Image.open(BytesIO(response.content))
image = preprocess_image(image)
return image
def load_image(image_url, image_size=256, dynamic_size=False, max_dynamic_size=512):
"""Loads and preprocesses images."""
# Cache image file locally.
if image_url in original_image_cache:
img = original_image_cache[image_url]
elif image_url.startswith('https://'):
img = load_image_from_url(image_url)
else:
fd = tf.io.gfile.GFile(image_url, 'rb')
img = preprocess_image(Image.open(fd))
original_image_cache[image_url] = img
# Load and convert to float32 numpy array, add batch dimension, and normalize to range [0, 1].
img_raw = img
if tf.reduce_max(img) > 1.0:
img = img / 255.
if len(img.shape) == 3:
img = tf.stack([img, img, img], axis=-1)
if not dynamic_size:
img = tf.image.resize_with_pad(img, image_size, image_size)
elif img.shape[1] > max_dynamic_size or img.shape[2] > max_dynamic_size:
img = tf.image.resize_with_pad(img, max_dynamic_size, max_dynamic_size)
return img, img_raw
image_size = 224
dynamic_size = False
model_name = "inception_v3"
model_handle_map = {
"efficientnetv2-s": "https://tfhub.dev/google/imagenet/efficientnet_v2_imagenet1k_s/classification/2",
"efficientnetv2-m": "https://tfhub.dev/google/imagenet/efficientnet_v2_imagenet1k_m/classification/2",
"efficientnetv2-l": "https://tfhub.dev/google/imagenet/efficientnet_v2_imagenet1k_l/classification/2",
"efficientnetv2-s-21k": "https://tfhub.dev/google/imagenet/efficientnet_v2_imagenet21k_s/classification/2",
"efficientnetv2-m-21k": "https://tfhub.dev/google/imagenet/efficientnet_v2_imagenet21k_m/classification/2",
"efficientnetv2-l-21k": "https://tfhub.dev/google/imagenet/efficientnet_v2_imagenet21k_l/classification/2",
"efficientnetv2-xl-21k": "https://tfhub.dev/google/imagenet/efficientnet_v2_imagenet21k_xl/classification/2",
"efficientnetv2-b0-21k": "https://tfhub.dev/google/imagenet/efficientnet_v2_imagenet21k_b0/classification/2",
"efficientnetv2-b1-21k": "https://tfhub.dev/google/imagenet/efficientnet_v2_imagenet21k_b1/classification/2",
"efficientnetv2-b2-21k": "https://tfhub.dev/google/imagenet/efficientnet_v2_imagenet21k_b2/classification/2",
"efficientnetv2-b3-21k": "https://tfhub.dev/google/imagenet/efficientnet_v2_imagenet21k_b3/classification/2",
"efficientnetv2-s-21k-ft1k": "https://tfhub.dev/google/imagenet/efficientnet_v2_imagenet21k_ft1k_s/classification/2",
"efficientnetv2-m-21k-ft1k": "https://tfhub.dev/google/imagenet/efficientnet_v2_imagenet21k_ft1k_m/classification/2",
"efficientnetv2-l-21k-ft1k": "https://tfhub.dev/google/imagenet/efficientnet_v2_imagenet21k_ft1k_l/classification/2",
"efficientnetv2-xl-21k-ft1k": "https://tfhub.dev/google/imagenet/efficientnet_v2_imagenet21k_ft1k_xl/classification/2",
"efficientnetv2-b0-21k-ft1k": "https://tfhub.dev/google/imagenet/efficientnet_v2_imagenet21k_ft1k_b0/classification/2",
"efficientnetv2-b1-21k-ft1k": "https://tfhub.dev/google/imagenet/efficientnet_v2_imagenet21k_ft1k_b1/classification/2",
"efficientnetv2-b2-21k-ft1k": "https://tfhub.dev/google/imagenet/efficientnet_v2_imagenet21k_ft1k_b2/classification/2",
"efficientnetv2-b3-21k-ft1k": "https://tfhub.dev/google/imagenet/efficientnet_v2_imagenet21k_ft1k_b3/classification/2",
"efficientnetv2-b0": "https://tfhub.dev/google/imagenet/efficientnet_v2_imagenet1k_b0/classification/2",
"efficientnetv2-b1": "https://tfhub.dev/google/imagenet/efficientnet_v2_imagenet1k_b1/classification/2",
"efficientnetv2-b2": "https://tfhub.dev/google/imagenet/efficientnet_v2_imagenet1k_b2/classification/2",
"efficientnetv2-b3": "https://tfhub.dev/google/imagenet/efficientnet_v2_imagenet1k_b3/classification/2",
"efficientnet_b0": "https://tfhub.dev/tensorflow/efficientnet/b0/classification/1",
"efficientnet_b1": "https://tfhub.dev/tensorflow/efficientnet/b1/classification/1",
"efficientnet_b2": "https://tfhub.dev/tensorflow/efficientnet/b2/classification/1",
"efficientnet_b3": "https://tfhub.dev/tensorflow/efficientnet/b3/classification/1",
"efficientnet_b4": "https://tfhub.dev/tensorflow/efficientnet/b4/classification/1",
"efficientnet_b5": "https://tfhub.dev/tensorflow/efficientnet/b5/classification/1",
"efficientnet_b6": "https://tfhub.dev/tensorflow/efficientnet/b6/classification/1",
"efficientnet_b7": "https://tfhub.dev/tensorflow/efficientnet/b7/classification/1",
"bit_s-r50x1": "https://tfhub.dev/google/bit/s-r50x1/ilsvrc2012_classification/1",
"inception_v3": "https://tfhub.dev/google/imagenet/inception_v3/classification/4",
"inception_resnet_v2": "https://tfhub.dev/google/imagenet/inception_resnet_v2/classification/4",
"resnet_v1_50": "https://tfhub.dev/google/imagenet/resnet_v1_50/classification/4",
"resnet_v1_101": "https://tfhub.dev/google/imagenet/resnet_v1_101/classification/4",
"resnet_v1_152": "https://tfhub.dev/google/imagenet/resnet_v1_152/classification/4",
"resnet_v2_50": "https://tfhub.dev/google/imagenet/resnet_v2_50/classification/4",
"resnet_v2_101": "https://tfhub.dev/google/imagenet/resnet_v2_101/classification/4",
"resnet_v2_152": "https://tfhub.dev/google/imagenet/resnet_v2_152/classification/4",
"nasnet_large": "https://tfhub.dev/google/imagenet/nasnet_large/classification/4",
"nasnet_mobile": "https://tfhub.dev/google/imagenet/nasnet_mobile/classification/4",
"pnasnet_large": "https://tfhub.dev/google/imagenet/pnasnet_large/classification/4",
"mobilenet_v2_100_224": "https://tfhub.dev/google/imagenet/mobilenet_v2_100_224/classification/4",
"mobilenet_v2_130_224": "https://tfhub.dev/google/imagenet/mobilenet_v2_130_224/classification/4",
"mobilenet_v2_140_224": "https://tfhub.dev/google/imagenet/mobilenet_v2_140_224/classification/4",
"mobilenet_v3_small_100_224": "https://tfhub.dev/google/imagenet/mobilenet_v3_small_100_224/classification/5",
"mobilenet_v3_small_075_224": "https://tfhub.dev/google/imagenet/mobilenet_v3_small_075_224/classification/5",
"mobilenet_v3_large_100_224": "https://tfhub.dev/google/imagenet/mobilenet_v3_large_100_224/classification/5",
"mobilenet_v3_large_075_224": "https://tfhub.dev/google/imagenet/mobilenet_v3_large_075_224/classification/5",
}
model_image_size_map = {
"efficientnetv2-s": 384,
"efficientnetv2-m": 480,
"efficientnetv2-l": 480,
"efficientnetv2-b0": 224,
"efficientnetv2-b1": 240,
"efficientnetv2-b2": 260,
"efficientnetv2-b3": 300,
"efficientnetv2-s-21k": 384,
"efficientnetv2-m-21k": 480,
"efficientnetv2-l-21k": 480,
"efficientnetv2-xl-21k": 512,
"efficientnetv2-b0-21k": 224,
"efficientnetv2-b1-21k": 240,
"efficientnetv2-b2-21k": 260,
"efficientnetv2-b3-21k": 300,
"efficientnetv2-s-21k-ft1k": 384,
"efficientnetv2-m-21k-ft1k": 480,
"efficientnetv2-l-21k-ft1k": 480,
"efficientnetv2-xl-21k-ft1k": 512,
"efficientnetv2-b0-21k-ft1k": 224,
"efficientnetv2-b1-21k-ft1k": 240,
"efficientnetv2-b2-21k-ft1k": 260,
"efficientnetv2-b3-21k-ft1k": 300,
"efficientnet_b0": 224,
"efficientnet_b1": 240,
"efficientnet_b2": 260,
"efficientnet_b3": 300,
"efficientnet_b4": 380,
"efficientnet_b5": 456,
"efficientnet_b6": 528,
"efficientnet_b7": 600,
"inception_v3": 299,
"inception_resnet_v2": 299,
"mobilenet_v2_100_224": 224,
"mobilenet_v2_130_224": 224,
"mobilenet_v2_140_224": 224,
"nasnet_large": 331,
"nasnet_mobile": 224,
"pnasnet_large": 331,
"resnet_v1_50": 224,
"resnet_v1_101": 224,
"resnet_v1_152": 224,
"resnet_v2_50": 224,
"resnet_v2_101": 224,
"resnet_v2_152": 224,
"mobilenet_v3_small_100_224": 224,
"mobilenet_v3_small_075_224": 224,
"mobilenet_v3_large_100_224": 224,
"mobilenet_v3_large_075_224": 224,
}
model_handle = model_handle_map[model_name]
max_dynamic_size = 512
if model_name in model_image_size_map:
image_size = model_image_size_map[model_name]
dynamic_size = False
print(f"Images will be converted to {image_size}x{image_size}")
else:
dynamic_size = True
print(f"Images will be capped to a max size of {max_dynamic_size}x{max_dynamic_size}")
labels_file = "https://storage.googleapis.com/download.tensorflow.org/data/ImageNetLabels.txt"
#download labels and creates a maps
downloaded_file = tf.keras.utils.get_file("labels.txt", origin=labels_file)
classes = []
with open(downloaded_file) as f:
labels = f.readlines()
classes = [l.strip() for l in labels]
classifier = hub.load(model_handle)
def inference(img):
image, original_image = load_image(img, image_size, dynamic_size, max_dynamic_size)
input_shape = image.shape
warmup_input = tf.random.uniform(input_shape, 0, 1.0)
warmup_logits = classifier(warmup_input).numpy()
# Run model on image
probabilities = tf.nn.softmax(classifier(image)).numpy()
top_5 = tf.argsort(probabilities, axis=-1, direction="DESCENDING")[0][:5].numpy()
np_classes = np.array(classes)
# Some models include an additional 'background' class in the predictions, so
# we must account for this when reading the class labels.
includes_background_class = probabilities.shape[1] == 1001
result = {}
for i, item in enumerate(top_5):
class_index = item if includes_background_class else item + 1
line = f'({i+1}) {class_index:4} - {classes[class_index]}: {probabilities[0][top_5][i]}'
result[classes[class_index]] = probabilities[0][top_5][i].item()
return result
title="inception_v3"
description="Gradio Demo for inception_v3: [TF2] Imagenet (ILSVRC-2012-CLS) classification with Inception V3. To use it, simply upload your image or click on one of the examples to load them. Read more at the links below"
article = "<p style='text-align: center'><a href='https://tfhub.dev/google/imagenet/mobilenet_v3_large_075_224/classification/5' target='_blank'>Tensorflow Hub</a></p>"
examples=[['apple1.jpg']]
gr.Interface(inference,gr.inputs.Image(type="filepath"),"label",title=title,description=description,article=article,examples=examples).launch(enable_queue=True)