Qasim Wani
Qasim Wani
https://github.com/uvipen/Super-mario-bros-A3C-pytorch/blob/004d331c5f16022dfcf5d62d10574a7737db0bca/train.py#L49 In the first convolution layer in model.py, you specify the input channels as num_inputs. After digging through your repo, you're calling `create_train_env()` in `src/env.py` For Atari environments, breakout/pong/space-force, the...
adding paper on convex optimization for meta-learning - Provable Guarantees for Gradient-Based Meta-Learning
https://github.com/greydanus/baby-a3c/blob/85899d76bd1a72d9e9055ed35894390802e31240/baby-a3c.py#L72-L78 Why did you override the default implementation of step(closure)? The default one calculates exponential moving average. Your implementation doesn't calculate the step count because it always returns None. I...
Hi there. I had a question related to adding some time based dependency on the graph where we can have 2d convolution over multiple graphs differing in features/node. An approach...
Hey @karpathy , I created a high-level UML diagram showcasing what's going on at a high-level in [gpt.py](https://github.com/karpathy/ng-video-lecture/blob/master/gpt.py). This will make it easier for folks to _hack_ the rest of...
Great work! For beginners, here's a graphical representation of your code. Feel free to embed it in your scripts: https://gctpy.com/graph/1ca770a1905176a355836d485ee7c8fc5b97e74ae058fce332ca59fdcf4ac919. It shows how different functions connect to other functions in...
hey! I used [Graphical Code Tracer](https://github.com/QasimWani/gct) to create a UML diagram of [babyagi.py](https://github.com/yoheinakajima/babyagi/blob/main/babyagi.py) to help beginners understand your code. Would love it if you could attach it to the readme....
https://github.com/dragen1860/MAML-Pytorch/blob/98a00d41724c133bd29619a2fb2cc46dd128a368/meta.py#L41 hey, I'm confused why you didn't use the standard grad clipping function `nn.utils.clip_grad_norm(parameters, max_value)` instead of implementing `clip_grad_by_norm_`?
Super cool. I have an existing pytorch project that has over 100 .to(device) calls. is there an easy way to transform our codebase to incorporate runhouse? or should i manually...