Partha Ghosh
Partha Ghosh
Hi, First of all thanks for the great work. I want to deploy deep learning with combination of RNNs and DNNs. I saw that you control the bot by moving...
Hi, The command provided ``` python demo.py --name=face_checkpoints --model=face --attn_layer=2,3 --kernel_size=2=5,3=3 --gpu_id=0 --dataset_mode=face --dataroot=./dataset/FaceForensics --results_dir=./demo_results/face ``` Seems to dump the source validation frames and extracted edges. However, how do I...
Updating the library so it can run several environment instances in parallel. This might give Nx speed up if there are N CPU cores are available. this is especially nice...
Adding some useful utility functions for transfer learning
This PR cascades on top of [Enabling dropout layers to be used in the actor and critic models. #150](https://github.com/matthiasplappert/keras-rl/pull/150). This just exposes the weight loading by name flag.
I used this command `python train.py --dataset I128_hdf5 --parallel --shuffle --num_workers 8 --batch_size 256 --load_in_mem --num_G_accumulations 8 --num_D_accumulations 8 --num_D_steps 1 --G_lr 1e-4 --D_lr 4e-4 --D_B2 0.999 --G_B2 0.999 --G_attn...
Can I download pre-trained weights for 512X512 or 256X256 models?
Hi I get the following errors while trying to use the Fused activation.Do any one have an idea why? Traceback (most recent call last): File "/is/ps2/pghosh/.virtualenvs/gif/lib/python3.6/site-packages/torch/utils/cpp_extension.py", line 960, in _build_extension_module...
you write in you blog https://yangkky.github.io/2019/07/08/distributed-pytorch-tutorial.html - . It’s also possible to have multiple worker processes that fetch data for each GPU. How can I enable this? I am running...
The generator seems to be barebone STG2 generator. And then it only generates a batch of images, which when fed to the video discriminator fails because of dimensionality issues. I...