I am trying to train my model, ssd_mobilenet_v2_fpnlite_320x320_coco17_tpu-8.tar.gz, unfortunately, this is what I got.
Does anyone have a solution for this?
InvalidArgumentError: Graph execution error:
image_size must contain 3 elements[4]
[[{{node RandomCropImage/sample_distorted_bounding_box/SampleDistortedBoundingBoxV2}}]]
[[MultiDeviceIteratorGetNextFromShard]]
[[RemoteCall]]
[[while/body/_1/IteratorGetNext]] [Op:__inference__dist_train_step_51958]
The issue is most likely related to images that are not RGB. Before loading any images, make sure to convert them to RGB (3 channels).
Please use the following code to see which image is not in RGB mode and delete it.
from PIL import Image
import os
path = 'PATH TO THE IMAGES'
for file in os.listdir(path):
extension = file.split('.')[-1]
# image extension could be png, jpg, etc
if extension == 'jpg':
filepath = path+file
img = Image.open(filepath)
if img.mode != 'RGB':
print(file+', '+img.mode)