Issue
I am using Python 3.9 and Jupyter Notebook to make inferences with an object detection model. I'm pretty new to this process so I'm having trouble exporting the images after the objects are detected. Here is my code:
import io
import os
import scipy.misc
import numpy as np
import six
import time
import glob
from IPython.display import display
from six import BytesIO
import matplotlib
import matplotlib.pyplot as plt
from PIL import Image, ImageDraw, ImageFont
import tensorflow as tf
from object_detection.utils import ops as utils_ops
from object_detection.utils import label_map_util
from object_detection.utils import visualization_utils as vis_util
%matplotlib inline
def load_image_into_numpy_array(path):
"""Load an image from file into a numpy array.
Puts image into numpy array to feed into tensorflow graph.
Note that by convention we put it into a numpy array with shape
(height, width, channels), where channels=3 for RGB.
Args:
path: a file path (this can be local or on colossus)
Returns:
uint8 numpy array with shape (img_height, img_width, 3)
"""
img_data = tf.io.gfile.GFile(path, 'rb').read()
image = Image.open(BytesIO(img_data))
(im_width, im_height) = image.size
return np.array(image.getdata()).reshape(
(im_height, im_width, 3)).astype(np.uint8)
category_index = label_map_util.create_category_index_from_labelmap("/home/model_directory/label_map.pbtxt", use_display_name=True)
tf.keras.backend.clear_session()
model = tf.saved_model.load(f'/home/inference_graph_directory/saved_model/')
def run_inference_for_single_image(model, image):
image = np.asarray(image)
# The input needs to be a tensor, convert it using `tf.convert_to_tensor`.
input_tensor = tf.convert_to_tensor(image)
# The model expects a batch of images, so add an axis with `tf.newaxis`.
input_tensor = input_tensor[tf.newaxis,...]
# Run inference
model_fn = model.signatures['serving_default']
output_dict = model_fn(input_tensor)
# All outputs are batches tensors.
# Convert to numpy arrays, and take index [0] to remove the batch dimension.
# We're only interested in the first num_detections.
num_detections = int(output_dict.pop('num_detections'))
output_dict = {key:value[0, :num_detections].numpy()
for key,value in output_dict.items()}
output_dict['num_detections'] = num_detections
# detection_classes should be ints.
output_dict['detection_classes'] = output_dict['detection_classes'].astype(np.int64)
# Handle models with masks:
if 'detection_masks' in output_dict:
# Reframe the the bbox mask to the image size.
detection_masks_reframed = utils_ops.reframe_box_masks_to_image_masks(
output_dict['detection_masks'], output_dict['detection_boxes'],
image.shape[0], image.shape[1])
detection_masks_reframed = tf.cast(detection_masks_reframed > 0.5,
tf.uint8)
output_dict['detection_masks_reframed'] = detection_masks_reframed.numpy()
return output_dict
for image_path in glob.glob('/home/image_directory/test_images/*.jpg'):
image_np = load_image_into_numpy_array(image_path)
output_dict = run_inference_for_single_image(model, image_np)
vis_util.visualize_boxes_and_labels_on_image_array(
image_np,
output_dict['detection_boxes'],
output_dict['detection_classes'],
output_dict['detection_scores'],
category_index,
instance_masks=output_dict.get('detection_masks_reframed', None),
use_normalized_coordinates=True,
line_thickness=8)
display(Image.fromarray(image_np))
An example of one of the resulting output is as follows: Image
However, as can be seen in the code, I have a whole directory of inferences to export and needing to write them to a location on my hard drive. I tried adding this to the last part of the code...
for image_path in glob.glob('/home/test_images/*.jpg'):
image_np = load_image_into_numpy_array(image_path)
output_dict = run_inference_for_single_image(model, image_np)
vis_util.visualize_boxes_and_labels_on_image_array(
image_np,
output_dict['detection_boxes'],
output_dict['detection_classes'],
output_dict['detection_scores'],
category_index,
instance_masks=output_dict.get('detection_masks_reframed', None),
use_normalized_coordinates=True,
line_thickness=8)
display(Image.fromarray(image_np))
Image.fromarray(image_np).save('/home/desired_folder/*.jpg')
...but only the last of the inference photos (in the directory) is written. How can I write all of the inference photos to my directory?
Solution
I don't think you can use a wildcard in the save statement here.
Image.fromarray(image_np).save('/home/desired_folder/*.jpg')
You expect the output files to have the same filenames as the input files, right? You can keep track of them when loading in the image and use that in you save statement. Something similar to this should work.
import glob
from pathlib import Path
from PIL import Image
for image_path in glob.glob('/home/test_images/*.jpg'):
filename = Path(image_path).name # get filename. there are many ways to do this
# .. do stuff
Image.fromarray(image_np).save(f'/home/desired_folder/{filename}')
Answered By - Pigeon
0 comments:
Post a Comment
Note: Only a member of this blog may post a comment.