ValueError when checking input: expected input_image_meta to have shape (14,) but got array with shape (15,)

[alic-xc]

I'm training my model on google colab, but it did not pass 1 Epoch 1/300

Using resnet50 as network backbone For Mask R-CNN model
Applying Default Augmentation on Dataset
Train 300 images
Validate 55 images
Checkpoint Path: /content/mask_rcnn_models
Selecting layers to train
Epoch 1/300
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-7-dd1acad94c9d> in <module>()
      8 train_maskrcnn.load_pretrained_model("mask_rcnn_coco.h5")
      9 train_maskrcnn.load_dataset("fingerlings")
---> 10 train_maskrcnn.train_model(num_epochs = 300, augmentation=True,  path_trained_models = "mask_rcnn_models")

8 frames
/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/training_utils_v1.py in standardize_input_data(data, names, shapes, check_batch_axis, exception_prefix)
    538                              ': expected ' + names[i] + ' to have shape ' +
    539                              str(shape) + ' but got array with shape ' +
--> 540                              str(data_shape))
    541   return data
    542 

ValueError: Error when checking input: expected input_image_meta to have shape (14,) but got array with shape (15,)

I don't know what is really wrong. i've been on it for hours.

[ayoolaolafenwa]

@alic-xc this kind of error is usually caused by specifying the wrong number of classes in the training configuration. Confirm that you specify the exact number of classes in your dataset in the the training configuration.

[alic-xc]

Yes, you're correct. I made a mistake while annotating my images.
i have fixed it

[PrakharPrashantSingh]

hi,
i am also facing same kind of error, i checked 5 times that my class names and count (i.e. 9 classes) are correct.. i just dont understand anything now.. please help me.

thanks

[chillum-codeX]

update your classes it will work

[PrakharPrashantSingh]

update your classes it will work

can you not see the above comments.. i checked my classes 5 times... and also the annotated images and annotations... its not working

[doubletaro]

me too.

[doubletaro]

The problem is the type is not the correct count.

[Dickoabc123]

@doubletaro Did you solve this folks? i get the message ValueError: Error when checking input: expected input_image_meta to have shape (None, 14) but got array with shape (2, 15)

Here is my config and I only have 1 class, but remembered to add one for the background so num_classes = 2

Configurations:
BACKBONE                       resnet101
BACKBONE_STRIDES               [4, 8, 16, 32, 64]
BATCH_SIZE                     2
BBOX_STD_DEV                   [0.1 0.1 0.2 0.2]
COMPUTE_BACKBONE_SHAPE         None
DETECTION_MAX_INSTANCES        100
DETECTION_MIN_CONFIDENCE       0.9
DETECTION_NMS_THRESHOLD        0.3
FPN_CLASSIF_FC_LAYERS_SIZE     1024
GPU_COUNT                      1
GRADIENT_CLIP_NORM             5.0
IMAGES_PER_GPU                 2
IMAGE_CHANNEL_COUNT            3
IMAGE_MAX_DIM                  640
IMAGE_META_SIZE                14
IMAGE_MIN_DIM                  640
IMAGE_MIN_SCALE                0
IMAGE_RESIZE_MODE              square
IMAGE_SHAPE                    [640 640   3]
LEARNING_MOMENTUM              0.9
LEARNING_RATE                  0.001
LOSS_WEIGHTS                   {'rpn_class_loss': 1.0, 'rpn_bbox_loss': 1.0, 'mrcnn_class_loss': 1.0, 'mrcnn_bbox_loss': 1.0, 'mrcnn_mask_loss': 1.0}
MASK_POOL_SIZE                 14
MASK_SHAPE                     [28, 28]
MAX_GT_INSTANCES               100
MEAN_PIXEL                     [123.7 116.8 103.9]
MINI_MASK_SHAPE                (56, 56)
NAME                           pole
NUM_CLASSES                    2
POOL_SIZE                      7
POST_NMS_ROIS_INFERENCE        1000
POST_NMS_ROIS_TRAINING         2000
PRE_NMS_LIMIT                  6000
ROI_POSITIVE_RATIO             0.33
RPN_ANCHOR_RATIOS              [0.5, 1, 2]
RPN_ANCHOR_SCALES              (32, 64, 128, 256, 512)
RPN_ANCHOR_STRIDE              1
RPN_BBOX_STD_DEV               [0.1 0.1 0.2 0.2]
RPN_NMS_THRESHOLD              0.7
RPN_TRAIN_ANCHORS_PER_IMAGE    256
STEPS_PER_EPOCH                730
TOP_DOWN_PYRAMID_SIZE          256
TRAIN_BN                       False
TRAIN_ROIS_PER_IMAGE           200
USE_MINI_MASK                  True
USE_RPN_ROIS                   True
VALIDATION_STEPS               182
WEIGHT_DECAY                   0.0001