Ahmed Osama
Ahmed Osama
I have used same image on both models , Torch model present a good output while the Coreml model changes the main picture color . i used this image for...
I have tried the coreml conversation on other repository here is the link of the repository :- [link](https://github.com/DmitryUlyanov/texture_nets ) they provide a pre trained model :- [model.t7](https://yadi.sk/d/GwL9jNJovBwQg) By running the...
**Screenshots** In NLU   In Dialogue 
⚠️ Before posting a new issue, please make sure that your issue hasn't already been resolved in another issue. **Describe the bug** By Default Botfront opens in chitchat project. This...
**Describe the bug** I am having a problem with the new NLU pipeline,  Numbers are misclassified when tested alone. previously it was working fine. **Old NLU Pipeline** ``` pipeline:...
**Describe the bug** ``` botfront-test-rasa | Traceback (most recent call last): botfront-test-rasa | File "/usr/local/lib/python3.6/site-packages/rasa/core/run.py", line 60, in _create_single_channel botfront-test-rasa | input_channel_class = rasa.utils.common.class_from_module_path(channel) botfront-test-rasa | File "/usr/local/lib/python3.6/site-packages/rasa/utils/common.py", line 193,...
I suspect this is a bug from the trained data. I would like to have suggestions if possible to solve this ------------------------ ### Environment * **Tesseract Version**: tesseract 4.0.0-beta.1-306-g45b11cd *...
Hi, i am trying to train models using Johnson model , bu what ever i try low images are appearing - i have tried to make the image width multiple...
I am using the following command to train the model **`th train.lua -data dataset -style_image ./AdobeStock_90768625.jpeg -style_size 600 -image_size 512 -model johnson -batch_size 4 -learning_rate 1e-2 -style_weight 10 -style_layers relu1_2,relu2_2,relu3_2,relu4_2...
I am trying to print the torch model options of training, I have used the provided model **model.t7** I am using this code to print the option ``` require 'torch'...