I am working on hand sign detection for ASL. I am using Tensor-flow’s object detection API. I have 12000 images and successfully trained my model for 10,000 steps but when detecting hand signs on an image from my test data the rectangle with detection does not show up, nor does it come up for real-time detection. Here is my code:
Image detection:
# Load pipeline config and build a detection model
configs = config_util.get_configs_from_pipeline_file(files['PIPELINE_CONFIG'])
detection_model = model_builder.build(model_config=configs['model'], is_training=False)
# Restore checkpoint
ckpt = tf.compat.v2.train.Checkpoint(model=detection_model)
ckpt.restore(os.path.join(paths['CHECKPOINT_PATH'], 'ckpt-11')).expect_partial()
@tf.function
def detect_fn(image):
image, shapes = detection_model.preprocess(image)
prediction_dict = detection_model.predict(image, shapes)
detections = detection_model.postprocess(prediction_dict, shapes)
return detections
import cv2
import numpy as np
from matplotlib import pyplot as plt
%matplotlib inline
category_index = label_map_util.create_category_index_from_labelmap(files['LABELMAP'])
IMAGE_PATH = os.path.join(paths['IMAGE_PATH'], 'test', 'I.8ce2a238-370d-11ed-9b7a-acde48001122.jpg')
img = cv2.imread(IMAGE_PATH)
image_np = np.array(img)
input_tensor = tf.convert_to_tensor(np.expand_dims(image_np, 0), dtype=tf.float32)
detections = detect_fn(input_tensor)
num_detections = int(detections.pop('num_detections'))
detections = {key: value[0, :num_detections].numpy()
for key, value in detections.items()}
detections['num_detections'] = num_detections
# detection_classes should be ints.
detections['detection_classes'] = detections['detection_classes'].astype(np.int64)
label_id_offset = 1
image_np_with_detections = image_np.copy()
viz_utils.visualize_boxes_and_labels_on_image_array(
image_np_with_detections,
detections['detection_boxes'],
detections['detection_classes']+label_id_offset,
detections['detection_scores'],
category_index,
use_normalized_coordinates=True,
max_boxes_to_draw=5,
min_score_thresh=.8,
agnostic_mode=False)
plt.imshow(cv2.cvtColor(image_np_with_detections, cv2.COLOR_BGR2RGB))
plt.show()
Here is my output with no box:
When I try the same for real-time object detection the camera start but the box does not show up.
Real-time Detection:
cap = cv2.VideoCapture(0)
width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
while cap.isOpened():
ret, frame = cap.read()
image_np = np.array(frame)
input_tensor = tf.convert_to_tensor(np.expand_dims(image_np, 0), dtype=tf.float32)
detections = detect_fn(input_tensor)
num_detections = int(detections.pop('num_detections'))
detections = {key: value[0, :num_detections].numpy()
for key, value in detections.items()}
detections['num_detections'] = num_detections
# detection_classes should be ints.
detections['detection_classes'] = detections['detection_classes'].astype(np.int64)
label_id_offset = 1
image_np_with_detections = image_np.copy()
viz_utils.visualize_boxes_and_labels_on_image_array(
image_np_with_detections,
detections['detection_boxes'],
detections['detection_classes']+label_id_offset,
detections['detection_scores'],
category_index,
use_normalized_coordinates=True,
max_boxes_to_draw=5,
min_score_thresh=.8,
agnostic_mode=False)
cv2.imshow('object detection', cv2.resize(image_np_with_detections, (800, 600)))
if cv2.waitKey(10) & 0xFF == ord('q'):
cap.release()
cv2.destroyAllWindows()
break
What am I doing wrong? How can I overcome this?
Would appreciate any help.
Edit:
I am using OpenCV-python==4.6.0.66