tensor2tensor not found! even installed t2t

[Paul0M]

Hi,

Ubuntu 1604
MiniConda3
Python3.6.5
TensorFlow1.8.0

I've cloned this repo and used python -m pip install -e . --user in the director
but when I prepare the dataset .tensor2tensor not found! promtps.
Dose anyone have any ideas?

compare_gan$ compare_gan_prepare_datasets.sh 
tensor2tensor not found!
compare_gan$ bash compare_gan/bin/compare_gan_prepare_datasets.sh 
tensor2tensor not found!

so I uninstall compare-gan and install tensor2tensor

compare_gan$ pip uninstall compare-gan
Uninstalling compare-gan-1.0:
  Would remove:
    /home/mp/miniconda3/lib/python3.6/site-packages/compare-gan.egg-link
Proceed (y/n)? y
  Successfully uninstalled compare-gan-1.0

compare_gan$ pip install tensor2tensor
Requirement already satisfied: pyasn1<0.5.0,>=0.4.1 in /home/mp/miniconda3/lib/python3.6/site-packages (from pyasn1-modules>=0.2.1->google-auth>=1.4.1->google-api-python-client->tensor2tensor) (0.4.3)
Installing collected packages: tensor2tensor
Successfully installed tensor2tensor-1.6.3

And again using pip install -e . or python -m pip install -e . --user and execute compare_gan_prepare_datasets.sh

$ compare_gan_prepare_datasets.sh 
tensor2tensor not found!

Successful for testing t2t

t2t-trainer \
  --generate_data \
  --data_dir=~/t2t_data \
  --output_dir=~/t2t_train/mnist \
  --problem=image_mnist \
  --model=shake_shake \
  --hparams_set=shake_shake_quick \
  --train_steps=1000 \
  --eval_steps=100

INFO:tensorflow:Finished evaluation at 2018-06-15-05:36:40
INFO:tensorflow:Saving dict for global step 1000: global_step = 1000, loss = 0.047610797, metrics-image_mnist/targets/accuracy = 0.9956, metrics-image_mnist/targets/accuracy_per_sequence = 0.9956, metrics-image_mnist/targets/accuracy_top5 = 1.0, metrics-image_mnist/targets/neg_log_perplexity = -0.015870268
INFO:tensorflow:Stop training model as max steps reached

[Jiajie-Mei]

Hello, I also encountered the same problem. I fixed the issue by modifying the install_requires and extras_require in the setup.py and rerun "python -m pip install -e . --user". Like this:

install_requires=[
'future',
'numpy',
'pillow',
'protobuf',
'tensor2tensor',
'tensorflow',
'tensorflow_gpu',
],
extras_require={

},

That is, I simply move the content of extras_require to install_requires. This makes the setup.py script install packages and create some binary files in ~/.local/bin. It seems that if you didn't do that, the "python -m pip install -e . --user" would never install the extra packages for you.

[cclauss]

What do you get when you python --version ?

[rhaps0dy]

Just edit compare_gan_prepare_datasets.sh to say T2T_DATAGEN="t2t-datagen" instead of the current line 18, and delete lines 22-26. Your $PATH environment variable will probably take care of the rest.

[Paul0M]

As @rhaps0dy says, this is an environment problem.
We can use which t2t-datagen to locate the real location and then edit line 18 in compare_gan_prepare_datasets.sh
Here is my conda envir: /home/ubuntu/hdd1/zip_data/Paul/miniconda3/bin/t2t-datagen