-
Notifications
You must be signed in to change notification settings - Fork 77
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
run python attention.py ,error is following. how to fix it ? thanks in advance! #21
Comments
try to change paramter for FreeRunIm2LatexAttention |
Any idea for this issue? |
latest-gpu-py3-im2latex-gpu-allinone-v1.0
my docker
use it for free
…--
At 2019-07-02 04:13:54, "Behzad Ousat" <notifications@github.com> wrote:
Any idea for this issue?
I tried changing the parameters but I got some other errors:
Traceback (most recent call last):
File "attention.py", line 37, in
out,state = tflib.ops.FreeRunIm2LatexAttention('AttLSTM',ctx,emb_seqs,EMB_DIM,ENC_DIM,DEC_DIM,D,H,W)
File "/home/behzad/deepProject/others/im2latex-tensorflow/tflib/ops.py", line 660, in FreeRunIm2LatexAttention
out = tf.nn.dynamic_rnn(cell, inputs, initial_state=h0_dec, sequence_length=seq_len, swap_memory=True)
File "/home/behzad/miniconda3/envs/deepLearning/lib/python2.7/site-packages/tensorflow/python/util/deprecation.py", line 324, in new_func
return func(*args, **kwargs)
File "/home/behzad/miniconda3/envs/deepLearning/lib/python2.7/site-packages/tensorflow/python/ops/rnn.py", line 707, in dynamic_rnn
dtype=dtype)
File "/home/behzad/miniconda3/envs/deepLearning/lib/python2.7/site-packages/tensorflow/python/ops/rnn.py", line 916, in _dynamic_rnn_loop
swap_memory=swap_memory)
File "/home/behzad/miniconda3/envs/deepLearning/lib/python2.7/site-packages/tensorflow/python/ops/control_flow_ops.py", line 3501, in while_loop
return_same_structure)
File "/home/behzad/miniconda3/envs/deepLearning/lib/python2.7/site-packages/tensorflow/python/ops/control_flow_ops.py", line 3012, in BuildLoop
pred, body, original_loop_vars, loop_vars, shape_invariants)
File "/home/behzad/miniconda3/envs/deepLearning/lib/python2.7/site-packages/tensorflow/python/ops/control_flow_ops.py", line 2937, in _BuildLoop
body_result = body(*packed_vars_for_body)
File "/home/behzad/miniconda3/envs/deepLearning/lib/python2.7/site-packages/tensorflow/python/ops/control_flow_ops.py", line 3456, in
body = lambda i, lv: (i + 1, orig_body(*lv))
File "/home/behzad/miniconda3/envs/deepLearning/lib/python2.7/site-packages/tensorflow/python/ops/rnn.py", line 882, in _time_step
skip_conditionals=True)
File "/home/behzad/miniconda3/envs/deepLearning/lib/python2.7/site-packages/tensorflow/python/ops/rnn.py", line 283, in _rnn_step
new_output, new_state = call_cell()
File "/home/behzad/miniconda3/envs/deepLearning/lib/python2.7/site-packages/tensorflow/python/ops/rnn.py", line 870, in
call_cell = lambda: cell(input_t, state)
File "/home/behzad/deepProject/others/im2latex-tensorflow/tflib/ops.py", line 558, in call
_input = tflib.ops.Embedding('Embedding',self._n_out,self._n_in,_input)
File "/home/behzad/deepProject/others/im2latex-tensorflow/tflib/ops.py", line 82, in Embedding
initializer('Normal',[n_symbols, output_dim],std=1.0/np.sqrt(n_symbols))
File "/home/behzad/deepProject/others/im2latex-tensorflow/tflib/ops.py", line 46, in initializer
return lasagne.init.Normal(std,mean).sample(shape)
File "/home/behzad/miniconda3/envs/deepLearning/lib/python2.7/site-packages/lasagne/init.py", line 65, in sample
return floatX(get_rng().normal(self.mean, self.std, size=shape))
File "mtrand.pyx", line 1657, in mtrand.RandomState.normal
File "mtrand.pyx", line 242, in mtrand.cont2_array_sc
TypeError: 'Tensor' object cannot be interpreted as an index
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub, or mute the thread.
|
Where can I find this? |
docker run --runtime=nvidia --rm -it aspnetcs88/dlp:latest-gpu-py3-im2latex-gpu-one sh im2latex.sh
…--
At 2019-07-03 13:56:20, "Behzad Ousat" <notifications@github.com> wrote:
Where can I find this?
I cannot find this image on dockerhub, actually nothing with the name 'im2latex'.
I would appreciate it if you could give a repo link or some other url.
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub, or mute the thread.
|
… --
At 2019-07-03 13:56:20, "Behzad Ousat" <notifications@github.com> wrote:
Where can I find this?
I cannot find this image on dockerhub, actually nothing with the name 'im2latex'.
I would appreciate it if you could give a repo link or some other url.
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub, or mute the thread.
|
Which university are you at? Can I go to you as a visiting scholar?
…--
At 2019-07-03 13:56:20, "Behzad Ousat" <notifications@github.com> wrote:
Where can I find this?
I cannot find this image on dockerhub, actually nothing with the name 'im2latex'.
I would appreciate it if you could give a repo link or some other url.
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub, or mute the thread.
|
Thanks for the image. I will try it ASAP. |
Do you have QQ account or wechat account?
…--
At 2019-07-03 14:34:30, "Behzad Ousat" <notifications@github.com> wrote:
Thanks for the image. I will try it ASAP.
Sharif University of Technology, I don't know actually.
Contact these guys:
http://ia.sharif.ir/
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub, or mute the thread.
|
Do you have a chat tool?
…--
At 2019-07-03 14:34:30, "Behzad Ousat" <notifications@github.com> wrote:
Thanks for the image. I will try it ASAP.
Sharif University of Technology, I don't know actually.
Contact these guys:
http://ia.sharif.ir/
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub, or mute the thread.
|
Would you like to give me the files in the following link,
https://buffalo.app.box.com/s/6gklgrotfd5drbxvdw2xtrt9i2ldmt01/file/311777457525
I can not download it
thank you in advance!
can you download the file in the following link?
https://buffalo.app.box.com/s/6gklgrotfd5drbxvdw2xtrt9i2ldmt01/file/311777457525
…--
At 2019-07-03 13:56:20, "Behzad Ousat" <notifications@github.com> wrote:
Where can I find this?
I cannot find this image on dockerhub, actually nothing with the name 'im2latex'.
I would appreciate it if you could give a repo link or some other url.
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub, or mute the thread.
|
Would you like to give me the files in the following link,
https://buffalo.app.box.com/s/6gklgrotfd5drbxvdw2xtrt9i2ldmt01/file/311777457525
I can not download it
thank you in advance!
can you download the file in the following link?
https://buffalo.app.box.com/s/6gklgrotfd5drbxvdw2xtrt9i2ldmt01/file/311777457525
…--
At 2019-07-03 14:34:30, "Behzad Ousat" <notifications@github.com> wrote:
Thanks for the image. I will try it ASAP.
Sharif University of Technology, I don't know actually.
Contact these guys:
http://ia.sharif.ir/
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub, or mute the thread.
|
WARNING (theano.tensor.blas): Using NumPy C-API based implementation for BLAS functions.
Traceback (most recent call last):
File "attention.py", line 37, in
out,state = tflib.ops.FreeRunIm2LatexAttention('AttLSTM',emb_seqs,ctx,EMB_DIM,ENC_DIM,DEC_DIM,D,H,W)
File "/home/rootx/me/im2latextensorflow/im2latex-tensorflow-master/tflib/ops.py", line 625, in FreeRunIm2LatexAttention
V = tf.transpose(ctx,[0,2,3,1]) # (B, H, W, D)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/array_ops.py", line 1420, in transpose
ret = transpose_fn(a, perm, name=name)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_array_ops.py", line 8927, in transpose
"Transpose", x=x, perm=perm, name=name)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
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/framework/ops.py", line 3274, in create_op
op_def=op_def)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1792, in init
control_input_ops)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1631, in _create_c_op
raise ValueError(str(e))
ValueError: Dimension must be 3 but is 4 for 'transpose' (op: 'Transpose') with input shapes: [?,?,80], [4].
The text was updated successfully, but these errors were encountered: