Dimension issue

[Annieliaquat]

Can someone help me out on how to resolve this issue. It was first detecting the test image in colab but when I run it again it gives me this error. And when it gives me the bounding box on the test image, the font size is too small. I have tried different methods but its not working. I am doing all this training and testing in colab.

Here is the code. Object detection Api setup runs successfully and model is trained and tested.
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,
line_thickness=9,
max_boxes_to_draw=5,
min_score_thresh=.3,
agnostic_mode=False)

image=cv2.resize(image_np_with_detections,(1500, 800),interpolation = cv2.INTER_NEAREST)
plt.imshow(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
plt.show()

Here is the error

File "/content/drive/MyDrive/Tensorflow/Research/models/research/object_detection/core/preprocessor.py", line 3327, in resize_image *
new_image = tf.image.resize_images(

ValueError: 'images' must have either 3 or 4 dimension

[kumarpriyanshu2k2]

Your camera is not taking the input
make sure you have deleted the extra cap.release() cell
and try to alter the numbers in cv2.VideoCapture(number) mostly its either 0 or 1

[Annieliaquat]

Your camera is not taking the input make sure you have deleted the extra cap.release() cell and try to alter the numbers in cv2.VideoCapture(number) mostly its either 0 or 1

No I am not using camera. I am detecting using image stored in a folder. This error is removed now thank you for your reply. Kindly can you guide me on my second problem which I have already asked above. This problem "And when it gives me the bounding box on the test image, the font size is too small. I have tried different methods but its not working. I am doing all this training and testing in colab." Please if you can give some guidance