我一直在从CPU上的tensorflow集线器运行Inception模块，但是输出非常慢。响应时间很高。因此，然后移至AWS GPU服务器（p2.xlarge）。并运行相同的代码。我所做的唯一更改是安装了tensorflow-gpu而不是tensorflow。但是结果却以相同的速度出现。您能帮忙提高速度吗？我需要对服务器或代码进行任何更改吗？预先感谢。
这是我的代码
# For running inference on the TF-Hub module.
import tensorflow as tf
import tensorflow_hub as hub
import pandas as pd
import matplotlib.pyplot as plt
import tempfile
from six.moves.urllib.request import urlopen
from six import BytesIO
import numpy as np
from PIL import Image
from PIL import ImageColor
from PIL import ImageDraw
from PIL import ImageFont
from PIL import ImageOps
def display_image(image):
fig = plt.figure(figsize=(20, 15))
plt.grid(False)
plt.imshow(image)
def download_and_resize_image(url, new_width=256, new_height=256,
display=False):
_, filename = tempfile.mkstemp(suffix=".jpg")
response = urlopen(url)
image_data = response.read()
image_data = BytesIO(image_data)
pil_image = Image.open(image_data)
pil_image = ImageOps.fit(pil_image, (new_width, new_height), Image.ANTIALIAS)
pil_image_rgb = pil_image.convert("RGB")
pil_image_rgb.save(filename, format="JPEG", quality=90)
print("Image downloaded to %s." % filename)
if display:
display_image(pil_image)
return filename
def draw_bounding_box_on_image(image,
ymin,
xmin,
ymax,
xmax,
color,
font,
thickness=4,
display_str_list=()):
"""Adds a bounding box to an image."""
draw = ImageDraw.Draw(image)
im_width, im_height = image.size
(left, right, top, bottom) = (xmin * im_width, xmax * im_width,
ymin * im_height, ymax * im_height)
draw.line([(left, top), (left, bottom), (right, bottom), (right, top),
(left, top)],
width=thickness,
fill=color)
# If the total height of the display strings added to the top of the bounding
# box exceeds the top of the image, stack the strings below the bounding box
# instead of above.
display_str_heights = [font.getsize(ds)[1] for ds in display_str_list]
# Each display_str has a top and bottom margin of 0.05x.
total_display_str_height = (1 + 2 * 0.05) * sum(display_str_heights)
if top > total_display_str_height:
text_bottom = top
else:
text_bottom = bottom + total_display_str_height
# Reverse list and print from bottom to top.
for display_str in display_str_list[::-1]:
text_width, text_height = font.getsize(display_str)
margin = np.ceil(0.05 * text_height)
draw.rectangle([(left, text_bottom - text_height - 2 * margin),
(left + text_width, text_bottom)],
fill=color)
draw.text((left + margin, text_bottom - text_height - margin),
display_str,
fill="black",
font=font)
text_bottom -= text_height - 2 * margin
def draw_boxes(image, boxes, class_names, scores, max_boxes=10, min_score=0.1):
"""Overlay labeled boxes on an image with formatted scores and label names."""
colors = list(ImageColor.colormap.values())
try:
font = ImageFont.truetype("/usr/share/fonts/truetype/liberation/LiberationSansNarrow-Regular.ttf",
25)
except IOError:
print("Font not found, using default font.")
font = ImageFont.load_default()
for i in range(min(boxes.shape[0], max_boxes)):
if scores[i] >= min_score:
ymin, xmin, ymax, xmax = tuple(boxes[i].tolist())
display_str = "{}: {}%".format(class_names[i].decode("ascii"),
int(100 * scores[i]))
color = colors[hash(class_names[i]) % len(colors)]
image_pil = Image.fromarray(np.uint8(image)).convert("RGB")
draw_bounding_box_on_image(
image_pil,
ymin,
xmin,
ymax,
xmax,
color,
font,
display_str_list=[display_str])
np.copyto(image, np.array(image_pil))
return image
#Downloading imagenet model
module_handle = "https://tfhub.dev/google/faster_rcnn/openimages_v4/inception_resnet_v2/1" #@param ["https://tfhub.dev/google/openimages_v4/ssd/mobilenet_v2/1", "https://tfhub.dev/google/faster_rcnn/openimages_v4/inception_resnet_v2/1"]
import datetime
print(datetime.datetime.now())
with tf.Graph().as_default():
detector = hub.Module(module_handle)
image_string_placeholder = tf.placeholder(tf.string)
decoded_image = tf.image.decode_jpeg(image_string_placeholder)
# Module accepts as input tensors of shape [1, height, width, 3], i.e. batch
# of size 1 and type tf.float32.
decoded_image_float = tf.image.convert_image_dtype(
image=decoded_image, dtype=tf.float32)
module_input = tf.expand_dims(decoded_image_float, 0)
result = detector(module_input, as_dict=True)
init_ops = [tf.global_variables_initializer(), tf.tables_initializer()]
session = tf.Session()
session.run(init_ops)
print(datetime.datetime.now())
#Test on image
image_urls = [
"https://ayo-ke-osaka.co.id/media/school-image/osaka-jls-2.jpg"]
col_names = ['label', 'score']
tag = pd.DataFrame(columns = col_names)
for image_url in image_urls:
image_path = download_and_resize_image(image_url, 640, 480)
with tf.gfile.Open(image_path, "rb") as binfile:
image_string = binfile.read()
result_out, image_out = session.run(
[result, decoded_image],
feed_dict={image_string_placeholder: image_string})
x0=result_out["detection_class_entities"]
x1=result_out["detection_scores"]
y1=x1[x1>0.1]
elements=len(y1)
y0=x0[0:elements]
y0=y0.astype(str)
tags = pd.DataFrame({'label': y0, 'score': y1}, columns=['label', 'score'])
print(tags)
tag = tag.append(tags)