ryanwebster90

usage: gcc -O3 -shared -fPIC tm_vm_wordsim.c -o libtm_vm_wordsim.so

python3 wordsim_main.py --in bb6_machines.txt --out bb6_cpp.csv --steps 10000000 --bits 16 --skip-py --batch-c --entry-timeout=128

ryanwebster90

# Dynamic visualization of 2-symbol TM's. After --warmup steps, bits on the tape are regrouped into bytes and color-mapped, 
# then the 1D tape is reshaped and truncated from the left to a 64x64 frame to be recorded every --frame-every steps for --vis frames.
# ## Example usage:
# https://bbchallenge.org/76708232
# python vis_tm_bytes.py 
# https://bbchallenge.org/43374927
# python vis_tm_bytes.py --tm=1RB0RD_1LC1LB_1RA0LB_0RE1RD_---1RA --warmup=200_000_000 
# For 6-state machines, use a larger warmup (current BB(6) champion family)
# python vis_tm_bytes.py --warmup=200_000_000 --vis=80_000_000 --frame-every=100_000 --tm=1RB1RA_1RC1RZ_1LD0RF_1RA0LE_0LD1RC_1RA0RE --side=64

ryanwebster90

from diffusers import StableDiffusionPipeline, EulerDiscreteScheduler
import torch
scheduler = EulerDiscreteScheduler(use_karras_sigmas=True)
pipe = StableDiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5",scheduler=scheduler, torch_dtype=torch.float16)
generator = torch.Generator("cuda").manual_seed(0)
pipe = pipe.to('cuda')
image = pipe("a golden retriever",num_inference_steps=30,generator=generator).images[0]
image.save('test.jpg')

ryanwebster90

import numpy as np
import torch
import fire
import glob

def abs_ind_to_feat_file(abs_ind, cum_sz, feat_files):
    inds = np.argwhere(abs_ind - cum_sz >= 0)
    last_ind = inds[-1].item()
    ind_offset = cum_sz[last_ind]
    local_ind = abs_ind - ind_offset

ryanwebster90

{
    "model": {
        "type": "image_v1",
        "input_channels": 3,
        "input_size": [64, 64],
        "mapping_out": 256,
        "depths": [2, 2, 4, 4],
        "channels": [128, 256, 256, 512],
        "self_attn_depths": [false, false, true, true],
        "dropout_rate": 0.05,