Spaces:
Sleeping
Sleeping
File size: 2,876 Bytes
4094dc9 5f3320a 4094dc9 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 |
import tensorflow as tf
import numpy as np
import tensorflow_hub as hub
import keras
labels_path = keras.utils.get_file(
fname='labels.txt',
origin='https://raw.githubusercontent.com/tensorflow/models/f8af2291cced43fc9f1d9b41ddbf772ae7b0d7d2/official/projects/movinet/files/kinetics_600_labels.txt'
)
with open(labels_path, 'r', encoding='utf-8') as file:
lines = file.read().splitlines()
KINETICS_600_LABELS = np.array([line.strip() for line in lines])
KINETICS_600_LABELS[:20]
def main():
jumping_jack_path = 'assets/jumping_pack.gif'
jumping_jack = load_gif(jumping_jack_path)
id = 'a2'
mode = 'base'
version = '3'
hub_url = f'https://tfhub.dev/tensorflow/movinet/{id}/{mode}/kinetics-600/classification/{version}'
model = hub.load(hub_url)
sig = model.signatures['serving_default']
print('Model loaded.')
sig(image=jumping_jack[tf.newaxis, :1])
logits = sig(image=jumping_jack[tf.newaxis, ...])
logits = logits['classifier_head'][0]
probs = tf.nn.softmax(logits, axis=-1)
for label, p in get_top_k(probs):
print(f'{label:20s}: {p:.3f}')
def get_top_k(probs, k=5, label_map=KINETICS_600_LABELS):
"""Outputs the top k model labels and probabilities on the given video.
Args:
probs: probability tensor of shape (num_frames, num_classes) that represents
the probability of each class on each frame.
k: the number of top predictions to select.
label_map: a list of labels to map logit indices to label strings.
Returns:
a tuple of the top-k labels and probabilities.
"""
# Sort predictions to find top_k
top_predictions = tf.argsort(probs, axis=-1, direction='DESCENDING')[:k]
# collect the labels of top_k predictions
top_labels = tf.gather(label_map, top_predictions, axis=-1)
# decode labels
top_labels = [label.decode('utf8') for label in top_labels.numpy()]
# top_k probabilities of the predictions
top_probs = tf.gather(probs, top_predictions, axis=-1).numpy()
return tuple(zip(top_labels, top_probs))
def load_gif(file_path, image_size=(224, 224)):
"""Loads a gif file into a TF tensor.
Use images resized to match what's expected by your model.
The model pages say the "A2" models expect 224 x 224 images at 5 fps
Args:
file_path: path to the location of a gif file.
image_size: a tuple of target size.
Returns:
a video of the gif file
"""
# Load a gif file, convert it to a TF tensor
raw = tf.io.read_file(file_path)
video = tf.io.decode_gif(raw)
# Resize the video
video = tf.image.resize(video, image_size)
# change dtype to a float32
# Hub models always want images normalized to [0,1]
# ref: https://www.tensorflow.org/hub/common_signatures/images#input
video = tf.cast(video, tf.float32) / 255.
return video
|