Invalid argument: indices[0] = [0,148] is out of bounds: need 0 <= index < [32,6] about models HOT 8 CLOSED

Would you be able to provide more details about what you have modified and possibly the full log of running the model?

from models.

How can I create a inception model on a custom dataset (not flowers. I am piggy backing off the flowers train scripts)?

Below is the complete error
`$ bazel-bin/inception/flowers_train --train_dir="${TRAIN_DIR}" --data_dir="${FLOWERS_DATA_DIR}" --fine_tune=True --initial_learning_r
ate=0.001 --input_queue_memory_factor=1

W tensorflow/core/framework/op_kernel.cc:896] Invalid argument: indices[0] = [0,44] is out of bounds: need 0 <= index < [32,6]
Traceback (most recent call last):
File "/Users/k7/workspace/tensor_models/inception/bazel-bin/inception/flowers_train.runfiles/inception/flowers_train.py", line 41, in
tf.app.run()
File "/Library/Python/2.7/site-packages/tensorflow/python/platform/default/_app.py", line 30, in run
sys.exit(main(sys.argv))
File "/Users/k7/workspace/tensor_models/inception/bazel-bin/inception/flowers_train.runfiles/inception/flowers_train.py", line 37, in main
inception_train.train(dataset)
File "/Users/k7/workspace/tensor_models/inception/bazel-bin/inception/flowers_train.runfiles/inception/inception_train.py", line 332, in train
_, loss_value = sess.run([train_op, loss])
File "/Library/Python/2.7/site-packages/tensorflow/python/client/session.py", line 313, in run
return self._run(None, fetches, feed_dict)
File "/Library/Python/2.7/site-packages/tensorflow/python/client/session.py", line 509, in _run
feed_dict_string)
File "/Library/Python/2.7/site-packages/tensorflow/python/client/session.py", line 562, in _do_run
target_list)
File "/Library/Python/2.7/site-packages/tensorflow/python/client/session.py", line 584, in _do_call
e.code)
tensorflow.python.framework.errors.InvalidArgumentError: indices[0] = [0,44] is out of bounds: need 0 <= index < [32,6]
[[Node: tower_0/SparseToDense = SparseToDense[T=DT_FLOAT, Tindices=DT_INT32, validate_indices=true, _device="/job:localhost/replica:0/task:0/cpu:0"](tower_0/concat, tower_0/SparseToDense/output_shape, tower_0/SparseToDense/sparse_values, tower_0/SparseToDense/default_value)]]
Caused by op u'tower_0/SparseToDense', defined at:
File "/Users/k7/workspace/tensor_models/inception/bazel-bin/inception/flowers_train.runfiles/inception/flowers_train.py", line 41, in
tf.app.run()
File "/Library/Python/2.7/site-packages/tensorflow/python/platform/default/_app.py", line 30, in run
sys.exit(main(sys.argv))
File "/Users/k7/workspace/tensor_models/inception/bazel-bin/inception/flowers_train.runfiles/inception/flowers_train.py", line 37, in main
inception_train.train(dataset)
File "/Users/k7/workspace/tensor_models/inception/bazel-bin/inception/flowers_train.runfiles/inception/inception_train.py", line 235, in train
loss = _tower_loss(images, labels, num_classes, scope)
File "/Users/k7/workspace/tensor_models/inception/bazel-bin/inception/flowers_train.runfiles/inception/inception_train.py", line 115, in _tower_loss
inception.loss(logits, labels, batch_size=split_batch_size)
File "/Users/k7/workspace/tensor_models/inception/bazel-bin/inception/flowers_train.runfiles/inception/inception_model.py", line 125, in loss
1.0, 0.0)
File "/Library/Python/2.7/site-packages/tensorflow/python/ops/sparse_ops.py", line 362, in sparse_to_dense
name=name)
File "/Library/Python/2.7/site-packages/tensorflow/python/ops/gen_sparse_ops.py", line 362, in _sparse_to_dense
validate_indices=validate_indices, name=name)
File "/Library/Python/2.7/site-packages/tensorflow/python/ops/op_def_library.py", line 655, in apply_op
op_def=op_def)
File "/Library/Python/2.7/site-packages/tensorflow/python/framework/ops.py", line 2102, in create_op
original_op=self._default_original_op, op_def=op_def)
File "/Library/Python/2.7/site-packages/tensorflow/python/framework/ops.py", line 1129, in init
self._traceback = _extract_stack()`

from models.

Piggy-backing on the flowers data set is precisely our intention for releasing the example of the flowers data set, so I am glad it provides a good start.

Did you already generate the data and place it in $FLOWERS_DATA_DIR?

Also, if you did generate the new data set already, did you update num_classes() and num_examples_per_epoch() in flowers_data.py to correspond with your data?

https://github.com/tensorflow/models/blob/master/inception/inception/flowers_data.py#L34

from models.

Ah, didn't realize that I had explicitly set those (as that info could have been determined at runtime).

I have got the training script to run now. Thanks a lot for your help!

from models.

Hi, could this please become part of the writeup here: https://github.com/tensorflow/models/blob/master/inception/README.md

It has tripped me up and I'm sure others will also not realize that this needs to be done.

Thanks.

from models.

I am trying to build a model using flowers_train.py and got the same error. Here I changed the "examples" and "classes" for both flowers_data.py and build_image_data.py corresponding to my custom data. Still I am stuck with this error. Can anyone help me with this issue?

from models.

i have encounter this problem ,too. that indicates that your indicies do be out of bound . print it ,and check carefully. best wishes.

from models.

I meet the similar problem. I found my labels begin from 1 but not 0, so I changed the sequence of labels. Hope my answer can help you !

from models.