Nitish Bhardwaj

Hi @ranahanocka, thanks for your reply, I wanted to understand how do we create dataset for training a 3D model segmentation?

https://www.researchgate.net/publication/292074166_Mastering_the_game_of_Go_with_deep_neural_networks_and_tree_search

The package nolearn has been upgraded, and nolearn.convnet is deprecated. [Ref](https://pythonhosted.org/nolearn/decaf.html#nolearn.decaf.ConvNetFeatures) Use the below line to fix the issue. `from nolearn.decaf import ConvNeNetFeatures` To install the latest nolearn package, follow...

@wchen342 @rosdyana Have you tried it?

You need to download the [pre-trained model DAMSM for coco](https://drive.google.com/open?id=1zIrXCE9F6yfbEJIbNP5-YrEe2pZcPSGJ). Download, Extract and save the model files in the folder DAMSMencoders/.

Change the batch size defined in [cfg/eval_bird.yml](https://github.com/taoxugit/AttnGAN/blob/master/code/cfg/eval_bird.yml#L17). Updated parameters : ``` TRAIN: FLAG: True BATCH_SIZE: 16 ```

Follow instructions here https://github.com/TimoBolkart/BFM_to_FLAME#create-texture-model : _outputs a 'FLAME_albedo_from_BFM.npz'_