I'm working on a text summarization network and need to implement an
encoder to use with tf.nn.seq2seq.embedding_attention_decoder. As part of that I need to encode varying batches of sequences into representing vectors but the innermost encoding doesn't go through.
Here's a simplified snippet giving the same error:
import tensorflow as tf
single_cell = tf.nn.rnn_cell.GRUCell(1024)
sentence_cell = tf.nn.rnn_cell.EmbeddingWrapper(single_cell,
embedding_classes = 40000)
batch = [tf.placeholder(tf.int32, [1,1]) for _ in range(250)]
(_ , state) = tf.nn.rnn(sentence_cell, batch, dtype= tf.int32)
This fails with the following stack trace:
Traceback (most recent call last):
File "/home/ubuntu/workspace/example.py", line 6, in <module>
(_ , state) = tf.nn.rnn(sentence_cell, batch, dtype= tf.int32)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/rnn.py", line 126, in rnn
(output, state) = call_cell()
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/rnn.py", line 119, in <lambda>
call_cell = lambda: cell(input_, state)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/rnn_cell.py", line 616, in __call__
return self._cell(embedded, state)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/rnn_cell.py", line 150, in __call__
2 * self._num_units, True, 1.0))
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/rnn_cell.py", line 706, in linear
res = math_ops.matmul(array_ops.concat(1, args), matrix)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/array_ops.py", line 314, in concat
name=name)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_array_ops.py", line 70, in _concat
name=name)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/op_def_library.py", line 396, in apply_op
raise TypeError("%s that don't all match." % prefix)
TypeError: Tensors in list passed to 'values' of 'Concat' Op have types [float32, int32] that don't all match.
When debugging the input size of the sentence_cell is 1 and the elements in batch all have dimension [1,1] which is infact [batch_size, sentence_cell.input_size].
Switching to dtype = tf.float32 in the call to tf.nn.rnn() makes the snippet works but give me the following stack trace in my code:
[nltk_data] Downloading package punkt to /home/alex/nltk_data...
[nltk_data] Package punkt is already up-to-date!
Preparing news data in .
Creating 3 layers of 1024 units.
> /home/alex/Programmering/kandidatarbete/arbete/code/seq3seq/seq3seq_model.py(84)encode_sentence()
-> (_ ,state) = tf.nn.rnn(sentence_cell, sent, sequence_length = length, dtype= tf.float32)
(Pdb) c
Traceback (most recent call last):
File "translate.py", line 268, in <module>
tf.app.run()
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/platform/default/_app.py", line 30, in run
sys.exit(main(sys.argv))
File "translate.py", line 265, in main
train()
File "translate.py", line 161, in train
model = create_model(sess, False)
File "translate.py", line 136, in create_model
forward_only=forward_only)
File "/home/alex/Programmering/kandidatarbete/arbete/code/seq3seq/seq3seq_model.py", line 141, in __init__
softmax_loss_function=None)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/seq2seq.py", line 926, in model_with_buckets
decoder_inputs[:bucket[1]])
File "/home/alex/Programmering/kandidatarbete/arbete/code/seq3seq/seq3seq_model.py", line 140, in <lambda>
lambda x, y: seq3seq_f(x, y, False),
File "/home/alex/Programmering/kandidatarbete/arbete/code/seq3seq/seq3seq_model.py", line 98, in seq3seq_f
art_vecs = tfmap(encode_article, tf.pack(encoder_inputs))
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/control_flow_ops.py", line 1900, in map
_, r_a = While(lambda i, a: math_ops.less(i, n), compute, [i, acc_ta])
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/control_flow_ops.py", line 1557, in While
result = context.BuildLoop(cond, body, loop_vars)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/control_flow_ops.py", line 1474, in BuildLoop
body_result = body(*vars_for_body_with_tensor_arrays)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/control_flow_ops.py", line 1897, in compute
a = a.write(i, fn(elems_ta.read(i)))
File "/home/alex/Programmering/kandidatarbete/arbete/code/seq3seq/seq3seq_model.py", line 92, in encode_article
return tfmap(encode_sentence, article)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/control_flow_ops.py", line 1900, in map
_, r_a = While(lambda i, a: math_ops.less(i, n), compute, [i, acc_ta])
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/control_flow_ops.py", line 1557, in While
result = context.BuildLoop(cond, body, loop_vars)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/control_flow_ops.py", line 1474, in BuildLoop
body_result = body(*vars_for_body_with_tensor_arrays)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/control_flow_ops.py", line 1897, in compute
a = a.write(i, fn(elems_ta.read(i)))
File "/home/alex/Programmering/kandidatarbete/arbete/code/seq3seq/seq3seq_model.py", line 84, in encode_sentence
(_ ,state) = tf.nn.rnn(sentence_cell, sent, sequence_length = length, dtype= tf.float32)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/rnn.py", line 124, in rnn
zero_output, state, call_cell)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/rnn.py", line 212, in _rnn_step
time < max_sequence_length, call_cell, empty_update)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/control_flow_ops.py", line 1183, in cond
res_t = context_t.BuildCondBranch(fn1)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/control_flow_ops.py", line 1106, in BuildCondBranch
r = fn()
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/rnn.py", line 119, in <lambda>
call_cell = lambda: cell(input_, state)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/rnn_cell.py", line 615, in __call__
embedding, array_ops.reshape(inputs, [-1]))
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/embedding_ops.py", line 86, in embedding_lookup
validate_indices=validate_indices)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_array_ops.py", line 423, in gather
validate_indices=validate_indices, name=name)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/op_def_library.py", line 486, in apply_op
_Attr(op_def, input_arg.type_attr))
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/op_def_library.py", line 59, in _SatisfiesTypeConstraint
", ".join(dtypes.as_dtype(x).name for x in allowed_list)))
TypeError: DataType float32 for attr 'Tindices' not in list of allowed values: int32, int64
What am I missing?
Related
here is where i load my model:
_model = r"C:\Users\evead\Desktop\spacy_model_config_03_15\model-best"
nlp = spacy.load(_model)
txt = "Below are my data loader and neural net. I have also included the output of my data loader when I retrieve a batch of data"
doc = nlp(txt)
here is the error I got
but I got the following error:
Exception has occurred: RuntimeError
input must have 3 dimensions, got 2
File "C:\Users\evead\Desktop\Issam\PIXITREND-CLASSIFIER\Annotation-Training\src\debug_entity.py", line 46, in <module>
doc = nlp(txt)
here is my complete error:
(env) PS C:\Users\evead\Desktop\Issam\PIXITREND-CLASSIFIER> python -m spacy evaluate C:\Users\evead\Desktop\spacy_model_config_03_15\model-best C:\Users\evead\Desktop\batchdata-3-15\train.spacy --output C:\Users\evead\Desktop\batchdata-3-15\res.json
Using CPU
C:\Users\evead\Desktop\Issam\PIXITREND-CLASSIFIER\Annotation-Training\env\lib\site-packages\torch\autocast_mode.py:141: UserWarning: User provided device_type of 'cuda', but CUDA is not available. Disabling
warnings.warn('User provided device_type of \'cuda\', but CUDA is not available. Disabling')
Traceback (most recent call last):
File "C:\Users\evead\AppData\Local\Programs\Python\Python39\lib\runpy.py", line 197, in _run_module_as_main
return _run_code(code, main_globals, None,
File "C:\Users\evead\AppData\Local\Programs\Python\Python39\lib\runpy.py", line 87, in _run_code
exec(code, run_globals)
File "C:\Users\evead\Desktop\Issam\PIXITREND-CLASSIFIER\Annotation-Training\env\lib\site-packages\spacy\__main__.py", line 4, in <module>
setup_cli()
File "C:\Users\evead\Desktop\Issam\PIXITREND-CLASSIFIER\Annotation-Training\env\lib\site-packages\spacy\cli\_util.py", line 71, in setup_cli
command(prog_name=COMMAND)
File "C:\Users\evead\Desktop\Issam\PIXITREND-CLASSIFIER\Annotation-Training\env\lib\site-packages\click\core.py", line 1128, in __call__
return self.main(*args, **kwargs)
File "C:\Users\evead\Desktop\Issam\PIXITREND-CLASSIFIER\Annotation-Training\env\lib\site-packages\click\core.py", line 1053, in main
rv = self.invoke(ctx)
File "C:\Users\evead\Desktop\Issam\PIXITREND-CLASSIFIER\Annotation-Training\env\lib\site-packages\click\core.py", line 1659, in invoke
return _process_result(sub_ctx.command.invoke(sub_ctx))
File "C:\Users\evead\Desktop\Issam\PIXITREND-CLASSIFIER\Annotation-Training\env\lib\site-packages\click\core.py", line 1395, in invoke
return ctx.invoke(self.callback, **ctx.params)
File "C:\Users\evead\Desktop\Issam\PIXITREND-CLASSIFIER\Annotation-Training\env\lib\site-packages\click\core.py", line 754, in invoke
return __callback(*args, **kwargs)
File "C:\Users\evead\Desktop\Issam\PIXITREND-CLASSIFIER\Annotation-Training\env\lib\site-packages\typer\main.py", line 500, in wrapper
return callback(**use_params) # type: ignore
File "C:\Users\evead\Desktop\Issam\PIXITREND-CLASSIFIER\Annotation-Training\env\lib\site-packages\spacy\cli\evaluate.py", line 42, in evaluate_cli
evaluate(
File "C:\Users\evead\Desktop\Issam\PIXITREND-CLASSIFIER\Annotation-Training\env\lib\site-packages\spacy\cli\evaluate.py", line 78, in evaluate
scores = nlp.evaluate(dev_dataset)
File "C:\Users\evead\Desktop\Issam\PIXITREND-CLASSIFIER\Annotation-Training\env\lib\site-packages\spacy\language.py", line 1415, in evaluate
for eg, doc in zip(examples, docs):
File "C:\Users\evead\Desktop\Issam\PIXITREND-CLASSIFIER\Annotation-Training\env\lib\site-packages\spacy\language.py", line 1575, in pipe
for doc in docs:
File "C:\Users\evead\Desktop\Issam\PIXITREND-CLASSIFIER\Annotation-Training\env\lib\site-packages\spacy\util.py", line 1598, in _pipe
yield from proc.pipe(docs, **kwargs)
File "spacy\pipeline\transition_parser.pyx", line 230, in pipe
File "C:\Users\evead\Desktop\Issam\PIXITREND-CLASSIFIER\Annotation-Training\env\lib\site-packages\spacy\util.py", line 1547, in minibatch
batch = list(itertools.islice(items, int(batch_size)))
File "C:\Users\evead\Desktop\Issam\PIXITREND-CLASSIFIER\Annotation-Training\env\lib\site-packages\spacy\util.py", line 1598, in _pipe
yield from proc.pipe(docs, **kwargs)
File "spacy\pipeline\trainable_pipe.pyx", line 79, in pipe
File "C:\Users\evead\Desktop\Issam\PIXITREND-CLASSIFIER\Annotation-Training\env\lib\site-packages\spacy\util.py", line 1617, in raise_error
raise e
File "spacy\pipeline\trainable_pipe.pyx", line 75, in spacy.pipeline.trainable_pipe.TrainablePipe.pipe
File "C:\Users\evead\Desktop\Issam\PIXITREND-CLASSIFIER\Annotation-Training\env\lib\site-packages\spacy\pipeline\tok2vec.py", line 125, in predict
tokvecs = self.model.predict(docs)
File "C:\Users\evead\Desktop\Issam\PIXITREND-CLASSIFIER\Annotation-Training\env\lib\site-packages\thinc\model.py", line 315, in predict
return self._func(self, X, is_train=False)[0]
File "C:\Users\evead\Desktop\Issam\PIXITREND-CLASSIFIER\Annotation-Training\env\lib\site-packages\thinc\layers\chain.py", line 54, in forward
Y, inc_layer_grad = layer(X, is_train=is_train)
File "C:\Users\evead\Desktop\Issam\PIXITREND-CLASSIFIER\Annotation-Training\env\lib\site-packages\thinc\model.py", line 291, in __call__
return self._func(self, X, is_train=is_train)
File "C:\Users\evead\Desktop\Issam\PIXITREND-CLASSIFIER\Annotation-Training\env\lib\site-packages\thinc\layers\with_array.py", line 40, in forward
return _list_forward(cast(Model[List2d, List2d], model), Xseq, is_train)
File "C:\Users\evead\Desktop\Issam\PIXITREND-CLASSIFIER\Annotation-Training\env\lib\site-packages\thinc\layers\with_array.py", line 76, in _list_forward
Yf, get_dXf = layer(Xf, is_train)
File "C:\Users\evead\Desktop\Issam\PIXITREND-CLASSIFIER\Annotation-Training\env\lib\site-packages\thinc\model.py", line 291, in __call__
return self._func(self, X, is_train=is_train)
File "C:\Users\evead\Desktop\Issam\PIXITREND-CLASSIFIER\Annotation-Training\env\lib\site-packages\thinc\layers\with_padded.py", line 36, in forward
Y, backprop = _array_forward(layer, cast(Floats3d, Xseq), is_train)
File "C:\Users\evead\Desktop\Issam\PIXITREND-CLASSIFIER\Annotation-Training\env\lib\site-packages\thinc\layers\with_padded.py", line 76, in _array_forward
Yp, get_dXp = layer(Xp, is_train)
File "C:\Users\evead\Desktop\Issam\PIXITREND-CLASSIFIER\Annotation-Training\env\lib\site-packages\thinc\model.py", line 291, in __call__
return self._func(self, X, is_train=is_train)
File "C:\Users\evead\Desktop\Issam\PIXITREND-CLASSIFIER\Annotation-Training\env\lib\site-packages\thinc\layers\with_padded.py", line 30, in forward
Y, backprop = layer(Xseq, is_train)
File "C:\Users\evead\Desktop\Issam\PIXITREND-CLASSIFIER\Annotation-Training\env\lib\site-packages\thinc\model.py", line 291, in __call__
return self._func(self, X, is_train=is_train)
File "C:\Users\evead\Desktop\Issam\PIXITREND-CLASSIFIER\Annotation-Training\env\lib\site-packages\thinc\layers\pytorchwrapper.py", line 134, in forward
Ytorch, torch_backprop = model.shims[0](Xtorch, is_train)
File "C:\Users\evead\Desktop\Issam\PIXITREND-CLASSIFIER\Annotation-Training\env\lib\site-packages\thinc\shims\pytorch.py", line 56, in __call__
return self.predict(inputs), lambda a: ...
File "C:\Users\evead\Desktop\Issam\PIXITREND-CLASSIFIER\Annotation-Training\env\lib\site-packages\thinc\shims\pytorch.py", line 66, in predict
outputs = self._model(*inputs.args, **inputs.kwargs)
File "C:\Users\evead\Desktop\Issam\PIXITREND-CLASSIFIER\Annotation-Training\env\lib\site-packages\torch\nn\modules\module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "C:\Users\evead\Desktop\Issam\PIXITREND-CLASSIFIER\Annotation-Training\env\lib\site-packages\torch\nn\modules\rnn.py", line 689, in forward
self.check_forward_args(input, hx, batch_sizes)
File "C:\Users\evead\Desktop\Issam\PIXITREND-CLASSIFIER\Annotation-Training\env\lib\site-packages\torch\nn\modules\rnn.py", line 632, in check_forward_args
self.check_input(input, batch_sizes)
File "C:\Users\evead\Desktop\Issam\PIXITREND-CLASSIFIER\Annotation-Training\env\lib\site-packages\torch\nn\modules\rnn.py", line 201, in check_input
raise RuntimeError(
RuntimeError: input must have 3 dimensions, got 2
I am trying to train Autoencoder by Chainer in python and wrote below code. But it does not work. Why??
class Autoencoder(Chain):
def __init__(self):
super().__init__()
with self.init_scope():
self.l1 = L.Linear(3,2)
self.l2 = L.Linear(2,3)
def __call__(self,x):
h1 = self.l1(x)
h2 = self.l2(h1)
return h2
class Dataset(dataset.DatasetMixin):
def __init__(self,number_of_data, show_initial = False):
noise_level = 1
self.data = np.zeros((number_of_data,3),dtype = np.float32)
OA_vector = np.array([3,2,1])
OB_vector = np.array([2,-1,1])
t = np.random.uniform(-0.5,0.5,number_of_data)
s = np.random.uniform(-0.5,0.5,number_of_data)
for i in range(0,number_of_data):
noise = np.random.uniform(-noise_level, noise_level,3)
self.data[i] = t[i]*OA_vector + s[i]*OB_vector + noise
def __len__(self):
return self.data.shape[0]
def get_example(self,idx):
return self.data[idx]
if __name__ == "__main__":
n_epoch = 5
batch_size = 100
number_of_data = 1000 #データ数
train_data = Dataset(number_of_data,False)
model = Autoencoder()
optimizer = optimizers.SGD(lr=0.05).setup(model)
train_iter = iterators.SerialIterator(train_data,batch_size)
updater = training.StandardUpdater(train_iter,optimizer,device=0)
trainer = training.Trainer(updater,(n_epoch,"epoch"),out="result")
trainer.run()
I am using Chainer. And the Dataset makes 3 dimensitonal vectors. The number of the vectors is "number_of_data".
Should I do that without using trainer?
I don't understand where problem is.
EDIT
When we run above code with device=0, we have error like below.
Exception in main training loop: Unsupported type <class 'NoneType'>
Traceback (most recent call last):
File "/home/****/.local/lib/python3.5/site-packages/chainer/training/trainer.py", line 308, in run
update()
File "/home/****/.local/lib/python3.5/site-packages/chainer/training/updaters/standard_updater.py", line 149, in update
self.update_core()
File "/home/****/.local/lib/python3.5/site-packages/chainer/training/updaters/standard_updater.py", line 164, in update_core
optimizer.update(loss_func, in_arrays)
File "/home/****/.local/lib/python3.5/site-packages/chainer/optimizer.py", line 655, in update
loss.backward(loss_scale=self._loss_scale)
File "/home/****/.local/lib/python3.5/site-packages/chainer/variable.py", line 966, in backward
self._backward_main(retain_grad, loss_scale)
File "/home/****/.local/lib/python3.5/site-packages/chainer/variable.py", line 1095, in _backward_main
target_input_indexes, out_grad, in_grad)
File "/home/****/.local/lib/python3.5/site-packages/chainer/function_node.py", line 548, in backward_accumulate
gxs = self.backward(target_input_indexes, grad_outputs)
File "/home/****/.local/lib/python3.5/site-packages/chainer/functions/activation/relu.py", line 73, in backward
return ReLUGrad2(y).apply((gy,))
File "/home/****/.local/lib/python3.5/site-packages/chainer/function_node.py", line 258, in apply
outputs = self.forward(in_data)
File "/home/****/.local/lib/python3.5/site-packages/chainer/function_node.py", line 368, in forward
return self.forward_cpu(inputs)
File "/home/****/.local/lib/python3.5/site-packages/chainer/functions/activation/relu.py", line 97, in forward_cpu
y = (self.b > 0) * inputs[0]
File "cupy/core/core.pyx", line 1310, in cupy.core.core.ndarray.__mul__
File "cupy/core/elementwise.pxi", line 753, in cupy.core.core.ufunc.__call__
File "cupy/core/elementwise.pxi", line 68, in cupy.core.core._preprocess_args
Will finalize trainer extensions and updater before reraising the exception.
Traceback (most recent call last):
File "AC.py", line 70, in <module>
trainer.run()
File "/home/****/.local/lib/python3.5/site-packages/chainer/training/trainer.py", line 322, in run
six.reraise(*sys.exc_info())
File "/home/****/.local/lib/python3.5/site-packages/six.py", line 693, in reraise
raise value
File "/home/****/.local/lib/python3.5/site-packages/chainer/training/trainer.py", line 308, in run
update()
File "/home/****/.local/lib/python3.5/site-packages/chainer/training/updaters/standard_updater.py", line 149, in update
self.update_core()
File "/home/****/.local/lib/python3.5/site-packages/chainer/training/updaters/standard_updater.py", line 164, in update_core
optimizer.update(loss_func, in_arrays)
File "/home/****/.local/lib/python3.5/site-packages/chainer/optimizer.py", line 655, in update
loss.backward(loss_scale=self._loss_scale)
File "/home/****/.local/lib/python3.5/site-packages/chainer/variable.py", line 966, in backward
self._backward_main(retain_grad, loss_scale)
File "/home/****/.local/lib/python3.5/site-packages/chainer/variable.py", line 1095, in _backward_main
target_input_indexes, out_grad, in_grad)
File "/home/****/.local/lib/python3.5/site-packages/chainer/function_node.py", line 548, in backward_accumulate
gxs = self.backward(target_input_indexes, grad_outputs)
File "/home/****/.local/lib/python3.5/site-packages/chainer/functions/activation/relu.py", line 73, in backward
return ReLUGrad2(y).apply((gy,))
File "/home/****/.local/lib/python3.5/site-packages/chainer/function_node.py", line 258, in apply
outputs = self.forward(in_data)
File "/home/****/.local/lib/python3.5/site-packages/chainer/function_node.py", line 368, in forward
return self.forward_cpu(inputs)
File "/home/****/.local/lib/python3.5/site-packages/chainer/functions/activation/relu.py", line 97, in forward_cpu
y = (self.b > 0) * inputs[0]
File "cupy/core/core.pyx", line 1310, in cupy.core.core.ndarray.__mul__
File "cupy/core/elementwise.pxi", line 753, in cupy.core.core.ufunc.__call__
File "cupy/core/elementwise.pxi", line 68, in cupy.core.core._preprocess_args
TypeError: Unsupported type <class 'NoneType'>
When we run above code with device=-1, we have error like below.
Exception in main training loop: unsupported operand type(s) for *: 'bool' and 'NoneType'
Traceback (most recent call last):
File "/home/****/.local/lib/python3.5/site-packages/chainer/training/trainer.py", line 308, in run
update()
File "/home/****/.local/lib/python3.5/site-packages/chainer/training/updaters/standard_updater.py", line 149, in update
self.update_core()
File "/home/****/.local/lib/python3.5/site-packages/chainer/training/updaters/standard_updater.py", line 164, in update_core
optimizer.update(loss_func, in_arrays)
File "/home/****/.local/lib/python3.5/site-packages/chainer/optimizer.py", line 655, in update
loss.backward(loss_scale=self._loss_scale)
File "/home/****/.local/lib/python3.5/site-packages/chainer/variable.py", line 966, in backward
self._backward_main(retain_grad, loss_scale)
File "/home/****/.local/lib/python3.5/site-packages/chainer/variable.py", line 1095, in _backward_main
target_input_indexes, out_grad, in_grad)
File "/home/****/.local/lib/python3.5/site-packages/chainer/function_node.py", line 548, in backward_accumulate
gxs = self.backward(target_input_indexes, grad_outputs)
File "/home/****/.local/lib/python3.5/site-packages/chainer/functions/activation/relu.py", line 73, in backward
return ReLUGrad2(y).apply((gy,))
File "/home/****/.local/lib/python3.5/site-packages/chainer/function_node.py", line 258, in apply
outputs = self.forward(in_data)
File "/home/****/.local/lib/python3.5/site-packages/chainer/function_node.py", line 368, in forward
return self.forward_cpu(inputs)
File "/home/****/.local/lib/python3.5/site-packages/chainer/functions/activation/relu.py", line 97, in forward_cpu
y = (self.b > 0) * inputs[0]
Will finalize trainer extensions and updater before reraising the exception.
Traceback (most recent call last):
File "AC.py", line 70, in <module>
trainer.run()
File "/home/****/.local/lib/python3.5/site-packages/chainer/training/trainer.py", line 322, in run
six.reraise(*sys.exc_info())
File "/home/****/.local/lib/python3.5/site-packages/six.py", line 693, in reraise
raise value
File "/home/****/.local/lib/python3.5/site-packages/chainer/training/trainer.py", line 308, in run
update()
File "/home/****/.local/lib/python3.5/site-packages/chainer/training/updaters/standard_updater.py", line 149, in update
self.update_core()
File "/home/****/.local/lib/python3.5/site-packages/chainer/training/updaters/standard_updater.py", line 164, in update_core
optimizer.update(loss_func, in_arrays)
File "/home/****/.local/lib/python3.5/site-packages/chainer/optimizer.py", line 655, in update
loss.backward(loss_scale=self._loss_scale)
File "/home/****/.local/lib/python3.5/site-packages/chainer/variable.py", line 966, in backward
self._backward_main(retain_grad, loss_scale)
File "/home/****/.local/lib/python3.5/site-packages/chainer/variable.py", line 1095, in _backward_main
target_input_indexes, out_grad, in_grad)
File "/home/****/.local/lib/python3.5/site-packages/chainer/function_node.py", line 548, in backward_accumulate
gxs = self.backward(target_input_indexes, grad_outputs)
File "/home/****/.local/lib/python3.5/site-packages/chainer/functions/activation/relu.py", line 73, in backward
return ReLUGrad2(y).apply((gy,))
File "/home/****/.local/lib/python3.5/site-packages/chainer/function_node.py", line 258, in apply
outputs = self.forward(in_data)
File "/home/****/.local/lib/python3.5/site-packages/chainer/function_node.py", line 368, in forward
return self.forward_cpu(inputs)
File "/home/****/.local/lib/python3.5/site-packages/chainer/functions/activation/relu.py", line 97, in forward_cpu
y = (self.b > 0) * inputs[0]
TypeError: unsupported operand type(s) for *: 'bool' and 'NoneType'
I think the model need to return loss in __call__ method.
Sample modification is as follows:
class Autoencoder(Chain):
def __init__(self):
super().__init__()
with self.init_scope():
self.l1 = L.Linear(3,2)
self.l2 = L.Linear(2,3)
def forward(self,x):
h1 = self.l1(x)
h2 = self.l2(h1)
return h2
def __call__(self,x):
h = self.forward(x)
# Instead of h, __call__ should return loss.
loss = F.mean_squared_error(h, x)
return loss
I know that I can use tensorflow.data.TextLineDataset for this but I'd like to write a customized function to create a DataSet from a generator.
I'm implementing the input function for the census income data like this
_CSV_COLUMNS = [
('age', tf.int32),
('workclass', tf.string),
('fnlwgt', tf.int32),
('education', tf.string),
('education_num', tf.int32),
('marital_status', tf.string),
('occupation', tf.string),
('relationship', tf.string),
('race', tf.string),
('gender', tf.string),
('capital_gain', tf.int32),
('capital_loss', tf.int32),
('hours_per_week', tf.int32),
('native_country', tf.string),
('income_bracket', tf.string),
]
def input_csv(data_file, num_epochs, batch_size):
df = pd.read_csv(data_file, header=None)
def gen():
for row in df.iterrows():
row = row[1]
yield dict(zip([n[0] for n in _CSV_COLUMNS[:14]], row[:14])), row[14] == '>50K'
return tf.data.Dataset.from_generator(gen, (dict(_CSV_COLUMNS[:14]), tf.bool))
When I try this function with the Estimator API, it results in this error:
InvalidArgumentError (see above for traceback): assertion failed: [Feature (key: age) cannot have rank 0. Given: Tensor(\"IteratorGetNext:0\", dtype=int32)] [Condition x > 0 did not hold element-wise:] [x (linear/linear_model_1/linear_model/age/Rank:0) = ] [0]
Any ideas? Thanks in advance.
Additional info:
I'm testing it with SageMaker local mode. The train_input_fn and model_fn are like
_NUMERIC_COLUMNS = [
tf.feature_column.numeric_column(c) for c in
['age', 'education_num', 'capital_gain', 'capital_loss', 'hours_per_week']
]
def model_fn(features, labels, mode, hyperparameters):
classifier = tf.estimator.LinearClassifier(_NUMERIC_COLUMNS)
return classifier.model_fn(features, labels, mode, None)
def train_input_fn(training_dir, hyperparameters):
return input_csv(os.path.join(training_dir, 'adult.data.csv'), 3, 20)
The traceback is like (I added 2 blank lines around my source.)
Caused by op 'linear/linear_model_1/linear_model/age/assert_positive/assert_less/Assert/Assert', defined at:
File "/usr/local/bin/entry.py", line 28, in <module>
modes[mode]()
File "/usr/local/lib/python3.6/site-packages/container_support/training.py", line 36, in start
fw.train()
File "/usr/local/lib/python3.6/site-packages/tf_container/train_entry_point.py", line 164, in train
train_wrapper.train()
File "/usr/local/lib/python3.6/site-packages/tf_container/trainer.py", line 73, in train
tf.estimator.train_and_evaluate(estimator=estimator, train_spec=train_spec, eval_spec=eval_spec)
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/estimator/training.py", line 451, in train_and_evaluate
return executor.run()
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/estimator/training.py", line 617, in run
getattr(self, task_to_run)()
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/estimator/training.py", line 654, in run_master
self._start_distributed_training(saving_listeners=saving_listeners)
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/estimator/training.py", line 767, in _start_distributed_training
saving_listeners=saving_listeners)
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/estimator/estimator.py", line 376, in train
loss = self._train_model(input_fn, hooks, saving_listeners)
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/estimator/estimator.py", line 1145, in _train_model
return self._train_model_default(input_fn, hooks, saving_listeners)
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/estimator/estimator.py", line 1170, in _train_model_default
features, labels, model_fn_lib.ModeKeys.TRAIN, self.config)
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/estimator/estimator.py", line 1133, in _call_model_fn
model_fn_results = self._model_fn(features=features, **kwargs)
File "/usr/local/lib/python3.6/site-packages/tf_container/trainer.py", line 108, in _model_fn
return self.customer_script.model_fn(features, labels, mode, params)
File "/opt/ml/code/train.py", line 32, in model_fn
return classifier.model_fn(features, labels, mode, None)
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/estimator/estimator.py", line 263, in public_model_fn
return self._call_model_fn(features, labels, mode, config)
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/estimator/estimator.py", line 1133, in _call_model_fn
model_fn_results = self._model_fn(features=features, **kwargs)
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/estimator/canned/linear.py", line 339, in _model_fn
sparse_combiner=sparse_combiner)
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/estimator/canned/linear.py", line 163, in _linear_model_fn
logits = logit_fn(features=features)
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/estimator/canned/linear.py", line 101, in linear_logit_fn
cols_to_vars=cols_to_vars)
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/feature_column/feature_column.py", line 464, in linear_model
retval = linear_model_layer(features) # pylint: disable=not-callable
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/keras/engine/base_layer.py", line 736, in __call__
outputs = self.call(inputs, *args, **kwargs)
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/feature_column/feature_column.py", line 647, in call
weighted_sum = layer(builder)
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/layers/base.py", line 362, in __call__
outputs = super(Layer, self).__call__(inputs, *args, **kwargs)
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/keras/engine/base_layer.py", line 736, in __call__
outputs = self.call(inputs, *args, **kwargs)
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/feature_column/feature_column.py", line 539, in call
weight_var=self._weight_var)
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/feature_column/feature_column.py", line 2030, in _create_weighted_sum
weight_var=weight_var)
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/feature_column/feature_column.py", line 2043, in _create_dense_column_weighted_sum
trainable=trainable)
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/feature_column/feature_column.py", line 2474, in _get_dense_tensor
return inputs.get(self)
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/feature_column/feature_column.py", line 2263, in get
transformed = column._transform_feature(self) # pylint: disable=protected-access
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/feature_column/feature_column.py", line 2442, in _transform_feature
input_tensor = inputs.get(self.key)
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/feature_column/feature_column.py", line 2250, in get
feature_tensor = self._get_raw_feature_as_tensor(key)
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/feature_column/feature_column.py", line 2312, in _get_raw_feature_as_tensor
key, feature_tensor))]):
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/ops/check_ops.py", line 198, in assert_positive
return assert_less(zero, x, data=data, summarize=summarize)
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/ops/check_ops.py", line 559, in assert_less
return control_flow_ops.Assert(condition, data, summarize=summarize)
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/util/tf_should_use.py", line 118, in wrapped
return _add_should_use_warning(fn(*args, **kwargs))
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/ops/control_flow_ops.py", line 149, in Assert
return gen_logging_ops._assert(condition, data, summarize, name="Assert")
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/ops/gen_logging_ops.py", line 51, in _assert
name=name)
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 454, in new_func
return func(*args, **kwargs)
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3155, in create_op
op_def=op_def)
File "/usr/local/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1717, in __init__
self._traceback = tf_stack.extract_stack()
You cannot create a Tensor object with different data types. Check out the official doc
You can consider encoding everything as a string as the documentation suggests, or one hot encoding and further preprocessing before converting to a tensor, depending on your application.
EDIT2
Ok so far i have tried with python3.5 -tf 1.10 and python 2.7 tf 1.10
I m still getting this error
Traceback (most recent call last):
File "object_detection/model_main.py", line 101, in <module>
tf.app.run()
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/platform/app.py", line 125, in run
_sys.exit(main(argv))
File "object_detection/model_main.py", line 97, in main
tf.estimator.train_and_evaluate(estimator, train_spec, eval_specs[0])
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/estimator/training.py", line 455, in train_and_evaluate
return executor.run()
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/estimator/training.py", line 594, in run
return self.run_local()
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/estimator/training.py", line 695, in run_local
saving_listeners=saving_listeners)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/estimator/estimator.py", line 354, in train
loss = self._train_model(input_fn, hooks, saving_listeners)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/estimator/estimator.py", line 1179, in _train_model
return self._train_model_default(input_fn, hooks, saving_listeners)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/estimator/estimator.py", line 1209, in _train_model_default
features, labels, model_fn_lib.ModeKeys.TRAIN, self.config)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/estimator/estimator.py", line 1167, in _call_model_fn
model_fn_results = self._model_fn(features=features, **kwargs)
File "/home/nvidia/tensorflow/models/research/object_detection/model_lib.py", line 287, in model_fn
prediction_dict, features[fields.InputDataFields.true_image_shape])
File "/home/nvidia/tensorflow/models/research/object_detection/meta_architectures/ssd_meta_arch.py", line 686, in loss
keypoints, weights)
File "/home/nvidia/tensorflow/models/research/object_detection/meta_architectures/ssd_meta_arch.py", line 859, in _assign_targets
groundtruth_weights_list)
File "/home/nvidia/tensorflow/models/research/object_detection/core/target_assigner.py", line 481, in batch_assign_targets
anchors, gt_boxes, gt_class_targets, unmatched_class_label, gt_weights)
File "/home/nvidia/tensorflow/models/research/object_detection/core/target_assigner.py", line 180, in assign
match = self._matcher.match(match_quality_matrix, **params)
File "/home/nvidia/tensorflow/models/research/object_detection/core/matcher.py", line 239, in match
return Match(self._match(similarity_matrix, **params),
File "/home/nvidia/tensorflow/models/research/object_detection/matchers/argmax_matcher.py", line 190, in _match
_match_when_rows_are_non_empty, _match_when_rows_are_empty)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/util/deprecation.py", line 488, in new_func
return func(*args, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/control_flow_ops.py", line 2074, in cond
orig_res_t, res_t = context_t.BuildCondBranch(true_fn)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/control_flow_ops.py", line 1920, in BuildCondBranch
original_result = fn()
File "/home/nvidia/tensorflow/models/research/object_detection/matchers/argmax_matcher.py", line 153, in _match_when_rows_are_non_empty
-1)
File "/home/nvidia/tensorflow/models/research/object_detection/matchers/argmax_matcher.py", line 203, in _set_values_using_indicator
indicator = tf.cast(1-indicator, x.dtype)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/math_ops.py", line 878, in r_binary_op_wrapper
x = ops.convert_to_tensor(x, dtype=y.dtype.base_dtype, name="x")
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1028, in convert_to_tensor
as_ref=False)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1124, in internal_convert_to_tensor
ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/constant_op.py", line 228, in _constant_tensor_conversion_function
return constant(v, dtype=dtype, name=name)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/constant_op.py", line 207, in constant
value, dtype=dtype, shape=shape, verify_shape=verify_shape))
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/tensor_util.py", line 442, in make_tensor_proto
_AssertCompatible(values, dtype)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/tensor_util.py", line 353, in _AssertCompatible
(dtype.name, repr(mismatch), type(mismatch).__name__))
TypeError: Expected bool, got 1 of type 'int' instead.
Has anybody tried to train on TX2 or is it for my case only and i did something wrong?
ORIGINAL
Trying to train on mobilenet ssd on Jetson TX2 (I know it is not for taining but i have no better option)
followed these guides
https://towardsdatascience.com/how-to-train-your-own-object-detector-with-tensorflows-object-detector-api-bec72ecfe1d9
https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/running_locally.md
Training runs on my laptop (CPU) fine but i get the following error on my TX2
Traceback (most recent call last):
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/op_def_library.py", line 510, in _apply_op_helper
preferred_dtype=default_dtype)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/ops.py", line 1040, in internal_convert_to_tensor
ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/ops.py", line 883, in _TensorTensorConversionFunction
(dtype.name, t.dtype.name, str(t)))
ValueError: Tensor conversion requested dtype int32 for Tensor with dtype float32: 'Tensor("Loss/Loss/huber_loss/Sub_1:0", shape=(24, 1917, 4), dtype=float32)'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "object_detection/model_main.py", line 101, in <module>
tf.app.run()
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/platform/app.py", line 126, in run
_sys.exit(main(argv))
File "object_detection/model_main.py", line 97, in main
tf.estimator.train_and_evaluate(estimator, train_spec, eval_specs[0])
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/estimator/training.py", line 425, in train_and_evaluate
executor.run()
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/estimator/training.py", line 504, in run
self.run_local()
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/estimator/training.py", line 636, in run_local
hooks=train_hooks)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/estimator/estimator.py", line 355, in train
loss = self._train_model(input_fn, hooks, saving_listeners)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/estimator/estimator.py", line 824, in _train_model
features, labels, model_fn_lib.ModeKeys.TRAIN, self.config)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/estimator/estimator.py", line 805, in _call_model_fn
model_fn_results = self._model_fn(features=features, **kwargs)
File "/home/nvidia/tensorflow/models/research/object_detection/model_lib.py", line 287, in model_fn
prediction_dict, features[fields.InputDataFields.true_image_shape])
File "/home/nvidia/tensorflow/models/research/object_detection/meta_architectures/ssd_meta_arch.py", line 708, in loss
weights=batch_reg_weights)
File "/home/nvidia/tensorflow/models/research/object_detection/core/losses.py", line 74, in __call__
return self._compute_loss(prediction_tensor, target_tensor, **params)
File "/home/nvidia/tensorflow/models/research/object_detection/core/losses.py", line 157, in _compute_loss
reduction=tf.losses.Reduction.NONE
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/losses/losses_impl.py", line 444, in huber_loss
math_ops.multiply(delta, linear))
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/math_ops.py", line 326, in multiply
return gen_math_ops.mul(x, y, name)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/gen_math_ops.py", line 4689, in mul
"Mul", x=x, y=y, name=name)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/op_def_library.py", line 546, in _apply_op_helper
inferred_from[input_arg.type_attr]))
TypeError: Input 'y' of 'Mul' Op has type float32 that does not match type int32 of argument 'x'.
NOTE:
Used precompiled wheels to install tensorflow
There was an error with protobuf compiler that has been solved by
removing this line
reserved 6; (line number 104)
in ssd.proto on object_detection/protos folder
I found this solution here but i couldnt find the link
Here is the script to start training
PIPELINE_CONFIG_PATH=/home/nvidia/testtraining/models/model/ssd_mobilenet_v1_pets.config
MODEL_DIR=/home/nvidia/testtraining/models/model/
NUM_TRAIN_STEPS=50000
NUM_EVAL_STEPS=2000
python3 object_detection/model_main.py \
--pipeline_config_path=${PIPELINE_CONFIG_PATH} \
--model_dir=${MODEL_DIR} \
--num_train_steps=${NUM_TRAIN_STEPS} \
--num_eval_steps=${NUM_EVAL_STEPS} \
--alsologtostderr
Laptop TF version 1.10.0
Jetson TX2 tf version 1.6.0-rc1
I m new to Ubuntu and Tensorflow so go easy on me :)
Thanks
EDIT:
It seems like line 546, in _apply_op_helper is some sort of error handling line.
I tried to fix this error with following edit. Added these. In /usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/math_ops.py Added these to line 236 just after define statement
import tensorflow as tf
y = tf.cast(y, x.dtype)
This created some other error message which is solved by editing /home/nvidia/tensorflow/models/research/object_detection/matchers/argmax_matcher.py line 203-204 to these
indicator = tf.cast(1-indicator, x.dtype)
return tf.add(tf.multiply(x, indicator), val * indicator)
But i m still getting error
Traceback (most recent call last):
File "object_detection/model_main.py", line 101, in <module>
tf.app.run()
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/platform/app.py", line 126, in run
_sys.exit(main(argv))
File "object_detection/model_main.py", line 97, in main
tf.estimator.train_and_evaluate(estimator, train_spec, eval_specs[0])
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/estimator/training.py", line 425, in train_and_evaluate
executor.run()
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/estimator/training.py", line 504, in run
self.run_local()
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/estimator/training.py", line 636, in run_local
hooks=train_hooks)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/estimator/estimator.py", line 355, in train
loss = self._train_model(input_fn, hooks, saving_listeners)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/estimator/estimator.py", line 824, in _train_model
features, labels, model_fn_lib.ModeKeys.TRAIN, self.config)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/estimator/estimator.py", line 805, in _call_model_fn
model_fn_results = self._model_fn(features=features, **kwargs)
File "/home/nvidia/tensorflow/models/research/object_detection/model_lib.py", line 287, in model_fn
prediction_dict, features[fields.InputDataFields.true_image_shape])
File "/home/nvidia/tensorflow/models/research/object_detection/meta_architectures/ssd_meta_arch.py", line 686, in loss
keypoints, weights)
File "/home/nvidia/tensorflow/models/research/object_detection/meta_architectures/ssd_meta_arch.py", line 859, in _assign_targets
groundtruth_weights_list)
File "/home/nvidia/tensorflow/models/research/object_detection/core/target_assigner.py", line 481, in batch_assign_targets
anchors, gt_boxes, gt_class_targets, unmatched_class_label, gt_weights)
File "/home/nvidia/tensorflow/models/research/object_detection/core/target_assigner.py", line 180, in assign
match = self._matcher.match(match_quality_matrix, **params)
File "/home/nvidia/tensorflow/models/research/object_detection/core/matcher.py", line 239, in match
return Match(self._match(similarity_matrix, **params),
File "/home/nvidia/tensorflow/models/research/object_detection/matchers/argmax_matcher.py", line 190, in _match
_match_when_rows_are_non_empty, _match_when_rows_are_empty)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/util/deprecation.py", line 432, in new_func
return func(*args, **kwargs)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/control_flow_ops.py", line 2047, in cond
orig_res_t, res_t = context_t.BuildCondBranch(true_fn)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/control_flow_ops.py", line 1897, in BuildCondBranch
original_result = fn()
File "/home/nvidia/tensorflow/models/research/object_detection/matchers/argmax_matcher.py", line 153, in _match_when_rows_are_non_empty
-1)
File "/home/nvidia/tensorflow/models/research/object_detection/matchers/argmax_matcher.py", line 203, in _set_values_using_indicator
indicator = tf.cast(1-indicator, x.dtype)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/ops/math_ops.py", line 983, in r_binary_op_wrapper
x = ops.convert_to_tensor(x, dtype=y.dtype.base_dtype, name="x")
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/ops.py", line 950, in convert_to_tensor
as_ref=False)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/ops.py", line 1040, in internal_convert_to_tensor
ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/constant_op.py", line 235, in _constant_tensor_conversion_function
return constant(v, dtype=dtype, name=name)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/constant_op.py", line 214, in constant
value, dtype=dtype, shape=shape, verify_shape=verify_shape))
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/tensor_util.py", line 433, in make_tensor_proto
_AssertCompatible(values, dtype)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/tensor_util.py", line 344, in _AssertCompatible
(dtype.name, repr(mismatch), type(mismatch).__name__))
TypeError: Expected bool, got 1 of type 'int' instead.
And this one is out of my leage
I think there is a huge compatability issues and i will just install tf 1.1 instead
I m open to new ideas though
The key to your problem is here(bottom of traceback):
TypeError: Input 'y' of 'Mul' Op has type float32 that does not match type int32 of argument 'x'.
your y has type float32, but argument - x(place where you pass this y to), needs to be int32.
Try using tf.cast(y, tf.int32) or something like that.
Sometimes there are some changes in tf/you use some older model versions. So this may happen from time to time.
So just open
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/op_def_library.py"
find line 546, and do that cast. (using sudo vim, i guess)
I'm kind of new to working with TensorFlow and my problem may be easy to solve, at least I hope so.
I'm trying to work with LSTMCell to predict the next label in a sequence.
Here is the code I'm using :
import tensorflow as tf
max_sequence_length = 1000
vector_length = 1
number_of_classes = 1000
batch_size = 50
num_hidden = 24
# Define graph
data = tf.placeholder(tf.int64, [None, max_sequence_length, vector_length])
# 0 must be a free class so that the mask can work
target = tf.placeholder(tf.int64, [None, max_sequence_length, number_of_classes + 1])
labels = tf.argmax(target, 2)
cell = tf.nn.rnn_cell.LSTMCell(num_hidden, state_is_tuple=True)
Then I try to get the real length of each sequence in the batch
no_of_batches = tf.shape(data)[0]
sequence_lengths = tf.zeros([batch_size])
for i in xrange(max_sequence_length):
data_at_t = tf.squeeze(tf.slice(data, [0,i,0],[-1,1,-1]))
t = tf.scalar_mul(i, tf.ones([batch_size]))
boolean = tf.not_equal(data_at_t, tf.zeros([no_of_batches, batch_size], dtype = tf.int64))
sequence_lengths = tf.select(boolean, t, sequence_lengths)
And finally I try to call tf.nn.dynamic_rnn :
outputs, state = tf.nn.dynamic_rnn(
cell = cell,
inputs = data,
sequence_length = max_sequence_length,
dtype = tf.float64
)
Then, I get a TypeError:
Traceback (most recent call last):
File "<stdin>", line 5, in <module>
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/rnn.py", line 830, in dynamic_rnn
dtype=dtype)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/rnn.py", line 997, in _dynamic_rnn_loop
swap_memory=swap_memory)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/control_flow_ops.py", line 1973, in while_loop
result = context.BuildLoop(cond, body, loop_vars)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/control_flow_ops.py", line 1860, in BuildLoop
pred, body, original_loop_vars, loop_vars)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/control_flow_ops.py", line 1810, in _BuildLoop
body_result = body(*packed_vars_for_body)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/rnn.py", line 980, in _time_step
skip_conditionals=True)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/rnn.py", line 394, in _rnn_step
new_output, new_state = call_cell()
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/rnn.py", line 968, in <lambda>
call_cell = lambda: cell(input_t, state)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/rnn_cell.py", line 489, in __call__
dtype, self._num_unit_shards)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/rnn_cell.py", line 323, in _get_concat_variable
sharded_variable = _get_sharded_variable(name, shape, dtype, num_shards)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/rnn_cell.py", line 353, in _get_sharded_variable
dtype=dtype))
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/variable_scope.py", line 830, in get_variable
custom_getter=custom_getter)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/variable_scope.py", line 673, in get_variable
custom_getter=custom_getter)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/variable_scope.py", line 217, in get_variable
validate_shape=validate_shape)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/variable_scope.py", line 202, in _true_getter
caching_device=caching_device, validate_shape=validate_shape)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/variable_scope.py", line 536, in _get_single_variable
validate_shape=validate_shape)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/variables.py", line 211, in __init__
dtype=dtype)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/variables.py", line 281, in _init_from_args
self._initial_value = ops.convert_to_tensor(initial_value(),
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/variable_scope.py", line 526, in <lambda>
init_val = lambda: initializer(shape.as_list(), dtype=dtype)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/init_ops.py", line 210, in _initializer
dtype, seed=seed)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/random_ops.py", line 235, in random_uniform
minval = ops.convert_to_tensor(minval, dtype=dtype, name="min")
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 621, in convert_to_tensor
ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/constant_op.py", line 180, in _constant_tensor_conversion_function
return constant(v, dtype=dtype, name=name)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/constant_op.py", line 163, in constant
tensor_util.make_tensor_proto(value, dtype=dtype, shape=shape))
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/tensor_util.py", line 353, in make_tensor_proto
_AssertCompatible(values, dtype)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/tensor_util.py", line 290, in _AssertCompatible
(dtype.name, repr(mismatch), type(mismatch).__name__))
TypeError: Expected int64, got -0.34641016151377546 of type 'float' instead.
I don't understand where this float comes from as all other values in the script are integers. How can I solve this problem ?
1) The RNN cell state is tf.float64. You set this explicitly within the tf.nn.dynamic_rnn call (dtype). The tensorflow engine then initialized the states with RNN's default random_uniform initializer. This is why you have the -0.34 float value there.
I'm not sure what you wanted to achieve. Please refer to https://www.tensorflow.org/versions/r0.11/api_docs/python/nn.html#dynamic_rnn
2) The sequence_length = max_sequence_length must be an int32/int64 vector sized [batch_size] instead of scalar 1000
3) You may want to initialize the LSTMCell state too:
cell = tf.nn.rnn_cell.LSTMCell(num_hidden, state_is_tuple=True),
initializer=tf.constant_initializer(value=0, dtype=tf.int32))
i have a similar problem with my code, i fixed it by replacing the int32 at the placeholder as float, check if that works