svpino / tf_object_detection_cm

Confusion Matrix in Object Detection with TensorFlow
78 stars 36 forks source link

confusion_matrix.py:116: RuntimeWarning: invalid value encountered in double_scalars recall = float(confusion_matrix[id, id] / total_target) #25

Open JerrySor opened 4 years ago

JerrySor commented 4 years ago

Instructions for updating: Use eager execution and: tf.data.TFRecordDataset(path) Processed 100 images Processed 200 images Processed 300 images Processed 400 images Processed 400 images

Confusion Matrix: (array([[ 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.], [ 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.], [ 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.], [ 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.], [ 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.], [ 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.], [ 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.], [ 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.], [ 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.], [ 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.], [ 83., 56., 53., 48., 92., 103., 94., 80., 15., 38., 150.]]), '\n') confusion_matrix.py:116: RuntimeWarning: invalid value encountered in double_scalars recall = float(confusion_matrix[id, id] / totaltarget) category precision@0.6IOU recall_@0.6IOU 1 0.0 NaN 2 0.0 NaN 3 0.0 NaN 4 0.0 NaN 5 0.0 NaN 6 0.0 NaN 7 0.0 NaN 8 0.0 NaN 9 0.0 NaN 0 0.0 NaN

could you explain me what is the problem?

sbetts2 commented 3 years ago

@JerrySor Hi, were you able to ever fix this problem? I am having the same issue...thanks!

JerrySor commented 3 years ago

I am not yet have solutions on it.

On Wed, Jun 23, 2021, 13:15 sbetts2 @.***> wrote:

@JerrySor https://github.com/JerrySor Hi, were you able to ever fix this problem? I am having the same issue...thanks!

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/svpino/tf_object_detection_cm/issues/25#issuecomment-866560393, or unsubscribe https://github.com/notifications/unsubscribe-auth/ANRPZJFZPONBJDNR2XVSWCLTUF3ZXANCNFSM4P4PKDIA .