-
Notifications
You must be signed in to change notification settings - Fork 46
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Train error #20
Comments
I got the same question here |
Changing the following line:
to match the one above it: labels = tf.pad(labels, [(0, P)], constant_values=0) # [num_rois] seems to make the training go through. |
khatchad
added a commit
to khatchad/tf-eager-fasterrcnn
that referenced
this issue
Aug 1, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
I executed the train_model.pynb but I have the following error:
InvalidArgumentError Traceback (most recent call last)
in
4 with tf.GradientTape() as tape:
5 rpn_class_loss, rpn_bbox_loss, rcnn_class_loss, rcnn_bbox_loss =
----> 6 model((batch_imgs, batch_metas, batch_bboxes, batch_labels), training=True)
7
8 loss_value = rpn_class_loss + rpn_bbox_loss + rcnn_class_loss + rcnn_bbox_loss
D:\faster2\detection\models\detectors\faster_rcnn.py in call(self, inputs, training)
133 rois, rcnn_labels, rcnn_label_weights, rcnn_delta_targets, rcnn_delta_weights =
134 self.bbox_target.build_targets(
--> 135 proposals, gt_boxes, gt_class_ids, img_metas)
136 else:
137 rois = proposals
D:\faster2\detection\core\bbox\bbox_target.py in build_targets(self, proposals, gt_boxes, gt_class_ids, img_metas)
71 for i in range(batch_size):
72 rois, labels, label_weights, delta_targets, delta_weights = self._build_single_target(
---> 73 proposals[i], gt_boxes[i], gt_class_ids[i], pad_shapes[i], i)
74 rcnn_rois.append(rois)
75 rcnn_labels.append(labels)
D:\faster2\detection\core\bbox\bbox_target.py in _build_single_target(self, proposals, gt_boxes, gt_class_ids, img_shape, batch_ind)
177 tile_delta_weights = tf.zeros((self.num_rcnn_deltas, self.num_classes, 4))
178 ids = tf.stack([tf.range(self.num_rcnn_deltas, dtype=labels.dtype), labels], axis=1)
--> 179 delta_targets = tf.tensor_scatter_nd_update(tile_delta_targets, ids, delta_targets) # [num_rois, self.num_classes, 4]
180 delta_weights = tf.tensor_scatter_nd_update(tile_delta_weights, ids, delta_weights) # [num_rois, self.num_classes, 4]
181
C:\ProgramData\Anaconda3\envs\faster\lib\site-packages\tensorflow_core\python\ops\gen_array_ops.py in tensor_scatter_update(tensor, indices, updates, name)
11081 else:
11082 message = e.message
C:\ProgramData\Anaconda3\envs\faster\lib\site-packages\six.py in raise_from(value, from_value)
InvalidArgumentError: indices[212] = [212, -1] does not index into shape [256,81,4] [Op:TensorScatterUpdate]
Can you help me to understand the problem? Thank you.
The text was updated successfully, but these errors were encountered: