Deep-Learning-TensorFlow

Deep-Learning-TensorFlow copied to clipboard

Thanks for offering this great repository! I found that https://github.com/gabrieleangeletti/Deep-Learning-TensorFlow/blob/ddeb1f2848da7b7bee166ad2152b4afc46bb2086/yadlt/models/linear/logistic_regression.py#L52-L55 may contain a numerical bug when the loss_func is "cross_entropy" since `self.mod_y` can be close to zero. To fix this,...

llylly

AttributeError: module 'tensorflow._api.v2.train' has no attribute 'GradientDescentOptimizer'

smmshahabi

LSTM: the problem of data serialization.

1

The input_data.shape is (35200, 22). The problem is as follows: ``` train_perplexity = self._run_train_step(train_set, 'train') File "F:\DBN-rbm-classification\yadlt\models\recurrent\lstm.py", line 92, in _run_train_step data, self.batch_size, self.num_steps)): File "F:\DBN-rbm-classification\yadlt\utils\utilities.py", line 77, in seq_data_iterator...

rosefun

'NoneType' object has no attribute 'run'

2

``` File "D:\DeepLearningInstall\anaconda3.5\lib\site-packages\yadlt\models\boltzmann\dbn.py", line 147, in _train_model self.tf_session.run( AttributeError: 'NoneType' object has no attribute 'run' ``` The lines in dbn.py is shown as follow: ``` for batch in batches: x_batch,...

rosefun

DBN finetuning issue

21

Hi, I started exploring the package yesterday. Started with the command line DBN example (same network and hyperparameters) as given in the documentation. ``` python command_line/run_dbn.py --dataset mnist --main_dir dbn-models...

mathurakhil

Always show Test accuracy 1.0 for run_stacked_autoencoder_supervised.py

1

I just try with the file after a slight modifying for my custom data **run_stacked_autoencoder_supervised.py** with doc configuation After running the code the output shows always test accuracy 1.0 ....

robi56

'DeepBeliefNetwork' object has no attribute 'model_predictions'

2

Hi, I saw that this problem had been resolved and the issue closed in April -- but I just pip installed yadlt today and continue to get this error. Thanks,...

mvkrein

Proble with different models!!

2

Hi, I am having problem in implementation of different models even in Example Usage! for example==>python run_dbn.py --dataset mnist --main_dir dbn-models --model_name my-deeper-dbn --verbose 1 --rbm_layers 512,256 --rbm_learning_rate 0.005 --rbm_num_epochs...

h3kt0rz

As my dataset is continous variables, I set the 'rbm_gauss_visible' True. However, I find that the performance of the model with pretraining is the same as without pretraining. I think...

rosefun

Sir, my code ran without errors but i couldnt get any output after making python autoencoder.py and enter and also in anaconda's spyder. If u can help me it will...

PatelAxita