You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I'm running through the tutorial here which uses the export.py script to save the yolov5l model to a saved file format. Running the following command returns an error:
The error is:
`TensorFlow SavedModel: export failure ❌ 2.4s: Exception encountered when calling layer 'sequential' (type Sequential).
One of the dimensions in the output is <= 0 due to downsampling in conv2d. Consider increasing the input size. Received input shape [1, 644, 644, 3] which would produce output shape with a zero or negative value in a dimension.
Call arguments received by layer 'sequential' (type Sequential):
• inputs=tf.Tensor(shape=(1, 640, 640, 3), dtype=float32)
• training=None
• mask=None`
I haven't changed anything in the repo, this is literally the first command I run after cloning it. I don't understand where the input shape parameters are being set. Any help would be appreciated. Thank you.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
I'm running through the tutorial here which uses the export.py script to save the yolov5l model to a saved file format. Running the following command returns an error:
python export.py --weights yolov5l.pt --include saved_model --nms
The error is:
`TensorFlow SavedModel: export failure ❌ 2.4s: Exception encountered when calling layer 'sequential' (type Sequential).
One of the dimensions in the output is <= 0 due to downsampling in conv2d. Consider increasing the input size. Received input shape [1, 644, 644, 3] which would produce output shape with a zero or negative value in a dimension.
Call arguments received by layer 'sequential' (type Sequential):
• inputs=tf.Tensor(shape=(1, 640, 640, 3), dtype=float32)
• training=None
• mask=None`
I haven't changed anything in the repo, this is literally the first command I run after cloning it. I don't understand where the input shape parameters are being set. Any help would be appreciated. Thank you.
Beta Was this translation helpful? Give feedback.
All reactions