Skip to content

Instantly share code, notes, and snippets.

Embed
What would you like to do?
# RUNNING INFERENCE
import numpy as np
import os
import cv2
import six.moves.urllib as urllib
import sys
import tarfile
import tensorflow as tf
import zipfile
from google.colab.patches import cv2_imshow
from collections import defaultdict
from io import StringIO
import matplotlib
import pandas as pd
import matplotlib.pyplot as plt
from PIL import Image
# This is needed since the notebook is stored in the object_detection folder.
sys.path.append("..")
from object_detection.utils import ops as utils_ops
# This is needed to display the images.
%matplotlib inline
from object_detection.utils import label_map_util
from object_detection.utils import visualization_utils as vis_util
# Change these values for the model used
num_classes = 2 # Change this value to the number of classes of the model
IMAGE_SIZE = (12, 8) # Output display size as you want
# Use images in test dir
IMAGE_DIR = "/mydrive/images"
IMAGE_PATHS = []
for file in os.listdir(IMAGE_DIR):
if file.endswith(".jpg") or file.endswith(".png"):
IMAGE_PATHS.append(os.path.join(IMAGE_DIR, file))
# Set paths to the trained model
PATH_TO_LABELS = '/content/gdrive/MyDrive/customTF1/data/label_map.pbtxt'
PATH_TO_CKPT = os.path.join(os.path.abspath("/content/gdrive/MyDrive/customTF1/data/inference_graph"), "frozen_inference_graph.pb")
# Set tensorflow graph
detection_graph = tf.Graph()
with detection_graph.as_default():
od_graph_def = tf.GraphDef()
with tf.gfile.GFile(PATH_TO_CKPT, 'rb') as fid:
serialized_graph = fid.read()
od_graph_def.ParseFromString(serialized_graph)
tf.import_graph_def(od_graph_def, name='')
# Set categories
label_map = label_map_util.load_labelmap(PATH_TO_LABELS)
categories = label_map_util.convert_label_map_to_categories(
label_map, max_num_classes=num_classes, use_display_name=True)
category_index = label_map_util.create_category_index(categories)
# Convert input image to a numpy array
def load_image_to_numpy(image):
(im_width, im_height) = image.size
return np.array(image.getdata()).reshape(
(im_height, im_width, 3)).astype(np.uint8)
# Inference pipeline
def run_inference(image, graph):
with graph.as_default():
with tf.Session() as sess:
# Get handles to input and output tensors
ops = tf.get_default_graph().get_operations()
all_tensor_names = {
output.name for op in ops for output in op.outputs}
tensor_dict = {}
for key in [
'num_detections', 'detection_boxes', 'detection_scores',
'detection_classes', 'detection_masks'
]:
tensor_name = key + ':0'
if tensor_name in all_tensor_names:
tensor_dict[key] = tf.get_default_graph().get_tensor_by_name(
tensor_name)
if 'detection_masks' in tensor_dict:
# The following processing is only for single image
detection_boxes = tf.squeeze(
tensor_dict['detection_boxes'], [0])
detection_masks = tf.squeeze(
tensor_dict['detection_masks'], [0])
# Reframe is required to translate mask from box coordinates to image coordinates and fit the image size.
real_num_detection = tf.cast(
tensor_dict['num_detections'][0], tf.int32)
detection_boxes = tf.slice(detection_boxes, [0, 0], [
real_num_detection, -1])
detection_masks = tf.slice(detection_masks, [0, 0, 0], [
real_num_detection, -1, -1])
detection_masks_reframed = utils_ops.reframe_box_masks_to_image_masks(
detection_masks, detection_boxes, image.shape[0], image.shape[1])
detection_masks_reframed = tf.cast(
tf.greater(detection_masks_reframed, .5), tf.uint8)
# Follow the convention by adding back the batch dimension
tensor_dict['detection_masks'] = tf.expand_dims(
detection_masks_reframed, 0)
image_tensor = tf.get_default_graph().get_tensor_by_name('image_tensor:0')
# Run inference
output_dict = sess.run(tensor_dict,
feed_dict={image_tensor: np.expand_dims(image, 0)})
# all outputs are float32 numpy arrays, so convert types as appropriate
output_dict['num_detections'] = int(
output_dict['num_detections'][0])
output_dict['detection_classes'] = output_dict[
'detection_classes'][0].astype(np.uint8)
output_dict['detection_boxes'] = output_dict['detection_boxes'][0]
output_dict['detection_scores'] = output_dict['detection_scores'][0]
if 'detection_masks' in output_dict:
output_dict['detection_masks'] = output_dict['detection_masks'][0]
return output_dict
# Run the inference for each image
for image_path in IMAGE_PATHS:
image = Image.open(image_path)
# Conver the image to numpy array
image_np = load_image_to_numpy(image)
# Expand dimensions since the model expects images to have shape: [1, None, None, 3]
image_np_expanded = np.expand_dims(image_np, axis=0)
# Perform the interence
output_dict = run_inference(image_np, detection_graph)
# Visualize
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'),
use_normalized_coordinates=True,
line_thickness=20,
min_score_thresh=0.1)
plt.figure(figsize=IMAGE_SIZE, dpi=200)
plt.axis("off")
plt.imshow(image_np)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment