Merge remote-tracking branch 'origin/main'
This commit is contained in:
Patrick Esser
commit
9fd981d790
|
|
@ -0,0 +1,149 @@
|
|||
model:
|
||||
base_learning_rate: 7.5e-05
|
||||
target: ldm.models.diffusion.ddpm.LatentInpaintDiffusion
|
||||
params:
|
||||
linear_start: 0.00085
|
||||
linear_end: 0.0120
|
||||
num_timesteps_cond: 1
|
||||
log_every_t: 200
|
||||
timesteps: 1000
|
||||
first_stage_key: "jpg"
|
||||
cond_stage_key: "txt"
|
||||
image_size: 64
|
||||
channels: 4
|
||||
cond_stage_trainable: false # Note: different from the one we trained before
|
||||
conditioning_key: hybrid # important
|
||||
monitor: val/loss_simple_ema
|
||||
scale_factor: 0.18215
|
||||
ckpt_path: "/fsx/stable-diffusion/stable-diffusion/checkpoints/v1pp/v1pp-flatlined-hr.ckpt"
|
||||
|
||||
scheduler_config: # 10000 warmup steps
|
||||
target: ldm.lr_scheduler.LambdaLinearScheduler
|
||||
params:
|
||||
warm_up_steps: [ 2500 ] # NOTE for resuming. use 10000 if starting from scratch
|
||||
cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
|
||||
f_start: [ 1.e-6 ]
|
||||
f_max: [ 1. ]
|
||||
f_min: [ 1. ]
|
||||
|
||||
unet_config:
|
||||
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
|
||||
params:
|
||||
image_size: 32 # unused
|
||||
in_channels: 9 # 4 data + 4 downscaled image + 1 mask
|
||||
out_channels: 4
|
||||
model_channels: 320
|
||||
attention_resolutions: [ 4, 2, 1 ]
|
||||
num_res_blocks: 2
|
||||
channel_mult: [ 1, 2, 4, 4 ]
|
||||
num_heads: 8
|
||||
use_spatial_transformer: True
|
||||
transformer_depth: 1
|
||||
context_dim: 768
|
||||
use_checkpoint: True
|
||||
legacy: False
|
||||
|
||||
first_stage_config:
|
||||
target: ldm.models.autoencoder.AutoencoderKL
|
||||
params:
|
||||
embed_dim: 4
|
||||
monitor: val/rec_loss
|
||||
ddconfig:
|
||||
double_z: true
|
||||
z_channels: 4
|
||||
resolution: 256
|
||||
in_channels: 3
|
||||
out_ch: 3
|
||||
ch: 128
|
||||
ch_mult:
|
||||
- 1
|
||||
- 2
|
||||
- 4
|
||||
- 4
|
||||
num_res_blocks: 2
|
||||
attn_resolutions: []
|
||||
dropout: 0.0
|
||||
lossconfig:
|
||||
target: torch.nn.Identity
|
||||
|
||||
cond_stage_config:
|
||||
target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
|
||||
|
||||
|
||||
data:
|
||||
target: ldm.data.laion.WebDataModuleFromConfig
|
||||
params:
|
||||
tar_base: "__improvedaesthetic__"
|
||||
batch_size: 2
|
||||
num_workers: 4
|
||||
multinode: True
|
||||
min_size: 512
|
||||
max_pwatermark: 0.8
|
||||
train:
|
||||
shards: '{00000..17279}.tar -'
|
||||
shuffle: 10000
|
||||
image_key: jpg
|
||||
image_transforms:
|
||||
- target: torchvision.transforms.Resize
|
||||
params:
|
||||
size: 512
|
||||
interpolation: 3
|
||||
- target: torchvision.transforms.RandomCrop
|
||||
params:
|
||||
size: 512
|
||||
postprocess:
|
||||
target: ldm.data.laion.AddMask
|
||||
params:
|
||||
mode: "512train-large"
|
||||
|
||||
# NOTE use enough shards to avoid empty validation loops in workers
|
||||
validation:
|
||||
shards: '{17280..17535}.tar -'
|
||||
shuffle: 0
|
||||
image_key: jpg
|
||||
image_transforms:
|
||||
- target: torchvision.transforms.Resize
|
||||
params:
|
||||
size: 512
|
||||
interpolation: 3
|
||||
- target: torchvision.transforms.CenterCrop
|
||||
params:
|
||||
size: 512
|
||||
postprocess:
|
||||
target: ldm.data.laion.AddMask
|
||||
params:
|
||||
mode: "512train-large"
|
||||
|
||||
|
||||
lightning:
|
||||
find_unused_parameters: False
|
||||
|
||||
modelcheckpoint:
|
||||
params:
|
||||
every_n_train_steps: 2000
|
||||
|
||||
callbacks:
|
||||
image_logger:
|
||||
target: main.ImageLogger
|
||||
params:
|
||||
disabled: False
|
||||
batch_frequency: 1000
|
||||
max_images: 4
|
||||
increase_log_steps: False
|
||||
log_first_step: False
|
||||
log_images_kwargs:
|
||||
use_ema_scope: False
|
||||
inpaint: False
|
||||
plot_progressive_rows: False
|
||||
plot_diffusion_rows: False
|
||||
N: 4
|
||||
unconditional_guidance_scale: 3.0
|
||||
unconditional_guidance_label: [""]
|
||||
ddim_steps: 100 # todo check these out for inpainting,
|
||||
ddim_eta: 1.0 # todo check these out for inpainting,
|
||||
|
||||
trainer:
|
||||
benchmark: True
|
||||
val_check_interval: 5000000 # really sorry
|
||||
num_sanity_val_steps: 0
|
||||
accumulate_grad_batches: 2
|
||||
|
|
@ -0,0 +1,214 @@
|
|||
model:
|
||||
base_learning_rate: 5.0e-05
|
||||
target: ldm.models.diffusion.ddpm.LatentUpscaleDiffusion
|
||||
params:
|
||||
low_scale_key: "lr"
|
||||
linear_start: 0.001
|
||||
linear_end: 0.015
|
||||
num_timesteps_cond: 1
|
||||
log_every_t: 200
|
||||
timesteps: 1000
|
||||
first_stage_key: "jpg"
|
||||
cond_stage_key: "txt"
|
||||
image_size: 32
|
||||
channels: 16
|
||||
cond_stage_trainable: false
|
||||
conditioning_key: "hybrid-adm"
|
||||
monitor: val/loss_simple_ema
|
||||
scale_factor: 0.22765929 # magic number
|
||||
|
||||
low_scale_config:
|
||||
target: ldm.modules.encoders.modules.LowScaleEncoder
|
||||
params:
|
||||
scale_factor: 0.18215
|
||||
linear_start: 0.00085
|
||||
linear_end: 0.0120
|
||||
timesteps: 1000
|
||||
max_noise_level: 250
|
||||
output_size: null
|
||||
model_config:
|
||||
target: ldm.models.autoencoder.AutoencoderKL
|
||||
params:
|
||||
embed_dim: 4
|
||||
monitor: val/rec_loss
|
||||
ckpt_path: "/fsx/stable-diffusion/stable-diffusion/models/first_stage_models/kl-f8/model.ckpt"
|
||||
ddconfig:
|
||||
double_z: true
|
||||
z_channels: 4
|
||||
resolution: 256
|
||||
in_channels: 3
|
||||
out_ch: 3
|
||||
ch: 128
|
||||
ch_mult:
|
||||
- 1
|
||||
- 2
|
||||
- 4
|
||||
- 4
|
||||
num_res_blocks: 2
|
||||
attn_resolutions: [ ]
|
||||
dropout: 0.0
|
||||
lossconfig:
|
||||
target: torch.nn.Identity
|
||||
|
||||
scheduler_config: # 10000 warmup steps
|
||||
target: ldm.lr_scheduler.LambdaLinearScheduler
|
||||
params:
|
||||
warm_up_steps: [ 10000 ]
|
||||
cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
|
||||
f_start: [ 1.e-6 ]
|
||||
f_max: [ 1. ]
|
||||
f_min: [ 1. ]
|
||||
|
||||
unet_config:
|
||||
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
|
||||
params:
|
||||
num_classes: 251 # timesteps for noise conditoining
|
||||
image_size: 64 # not really needed
|
||||
in_channels: 20
|
||||
out_channels: 16
|
||||
model_channels: 128
|
||||
attention_resolutions: [ 8, 4, 2 ] # -> at 32, 16, 8
|
||||
num_res_blocks: 2
|
||||
channel_mult: [ 1, 2, 4, 6, 8 ]
|
||||
# -> res, ds: (64, 1), (32, 2), (16, 4), (6, 8), (4, 16)
|
||||
num_heads: 8
|
||||
use_spatial_transformer: True
|
||||
transformer_depth: 1
|
||||
context_dim: 768
|
||||
use_checkpoint: True
|
||||
legacy: False
|
||||
|
||||
first_stage_config:
|
||||
target: ldm.models.autoencoder.AutoencoderKL
|
||||
params:
|
||||
embed_dim: 16
|
||||
monitor: val/rec_loss
|
||||
ckpt_path: "/fsx/stable-diffusion/stable-diffusion/models/first_stage_models/kl-f16/model.ckpt"
|
||||
ddconfig:
|
||||
double_z: True
|
||||
z_channels: 16
|
||||
resolution: 256
|
||||
in_channels: 3
|
||||
out_ch: 3
|
||||
ch: 128
|
||||
ch_mult: [ 1,1,2,2,4 ] # num_down = len(ch_mult)-1
|
||||
num_res_blocks: 2
|
||||
attn_resolutions: [ 16 ]
|
||||
dropout: 0.0
|
||||
lossconfig:
|
||||
target: torch.nn.Identity
|
||||
|
||||
cond_stage_config:
|
||||
target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
|
||||
|
||||
|
||||
#data: # TODO: finetune here later
|
||||
# target: ldm.data.laion.WebDataModuleFromConfig
|
||||
# params:
|
||||
# tar_base: "pipe:aws s3 cp s3://s-datasets/laion-high-resolution/"
|
||||
# batch_size: 10
|
||||
# num_workers: 4
|
||||
# train:
|
||||
# shards: '{00000..17279}.tar -'
|
||||
# shuffle: 10000
|
||||
# image_key: jpg
|
||||
# image_transforms:
|
||||
# - target: torchvision.transforms.Resize
|
||||
# params:
|
||||
# size: 1024
|
||||
# interpolation: 3
|
||||
# - target: torchvision.transforms.RandomCrop
|
||||
# params:
|
||||
# size: 1024
|
||||
# postprocess:
|
||||
# target: ldm.data.laion.AddLR
|
||||
# params:
|
||||
# factor: 2
|
||||
#
|
||||
# # NOTE use enough shards to avoid empty validation loops in workers
|
||||
# validation:
|
||||
# shards: '{17280..17535}.tar -'
|
||||
# shuffle: 0
|
||||
# image_key: jpg
|
||||
# image_transforms:
|
||||
# - target: torchvision.transforms.Resize
|
||||
# params:
|
||||
# size: 1024
|
||||
# interpolation: 3
|
||||
# - target: torchvision.transforms.CenterCrop
|
||||
# params:
|
||||
# size: 1024
|
||||
# postprocess:
|
||||
# target: ldm.data.laion.AddLR
|
||||
# params:
|
||||
# factor: 2
|
||||
|
||||
data:
|
||||
target: ldm.data.laion.WebDataModuleFromConfig
|
||||
params:
|
||||
tar_base: "__improvedaesthetic__"
|
||||
batch_size: 28
|
||||
num_workers: 4
|
||||
multinode: True
|
||||
min_size: 512
|
||||
train:
|
||||
shards: '{00000..17279}.tar -'
|
||||
shuffle: 10000
|
||||
image_key: jpg
|
||||
image_transforms:
|
||||
- target: torchvision.transforms.Resize
|
||||
params:
|
||||
size: 512
|
||||
interpolation: 3
|
||||
- target: torchvision.transforms.RandomCrop
|
||||
params:
|
||||
size: 512
|
||||
postprocess:
|
||||
target: ldm.data.laion.AddLR
|
||||
params:
|
||||
factor: 2
|
||||
|
||||
# NOTE use enough shards to avoid empty validation loops in workers
|
||||
validation:
|
||||
shards: '{17280..17535}.tar -'
|
||||
shuffle: 0
|
||||
image_key: jpg
|
||||
image_transforms:
|
||||
- target: torchvision.transforms.Resize
|
||||
params:
|
||||
size: 512
|
||||
interpolation: 3
|
||||
- target: torchvision.transforms.CenterCrop
|
||||
params:
|
||||
size: 512
|
||||
postprocess:
|
||||
target: ldm.data.laion.AddLR
|
||||
params:
|
||||
factor: 2
|
||||
|
||||
|
||||
lightning:
|
||||
find_unused_parameters: False
|
||||
|
||||
callbacks:
|
||||
image_logger:
|
||||
target: main.ImageLogger
|
||||
params:
|
||||
batch_frequency: 1000
|
||||
max_images: 4
|
||||
increase_log_steps: False
|
||||
log_first_step: False
|
||||
log_images_kwargs:
|
||||
use_ema_scope: False
|
||||
inpaint: False
|
||||
plot_progressive_rows: False
|
||||
plot_diffusion_rows: False
|
||||
N: 4
|
||||
unconditional_guidance_scale: 3.0
|
||||
unconditional_guidance_label: [""]
|
||||
|
||||
trainer:
|
||||
benchmark: True
|
||||
val_check_interval: 5000000 # really sorry
|
||||
num_sanity_val_steps: 0
|
||||
accumulate_grad_batches: 2
|
||||
|
|
@ -38,6 +38,18 @@ settings = {
|
|||
"max_s_box": 300,
|
||||
"marg": 10,
|
||||
},
|
||||
"512train-large": { # TODO: experimental
|
||||
"p_irr": 0.5,
|
||||
"min_n_irr": 1,
|
||||
"max_n_irr": 5,
|
||||
"max_l_irr": 450,
|
||||
"max_w_irr": 400,
|
||||
"min_n_box": 1,
|
||||
"max_n_box": 4,
|
||||
"min_s_box": 75,
|
||||
"max_s_box": 450,
|
||||
"marg": 10,
|
||||
},
|
||||
}
|
||||
|
||||
|
||||
|
|
@ -128,14 +140,18 @@ def gen_large_mask(prng, img_h, img_w,
|
|||
return mask
|
||||
|
||||
|
||||
make_lama_mask = lambda prng, h, w: gen_large_mask(prng, h, w,
|
||||
**settings["256train"])
|
||||
make_lama_mask = lambda prng, h, w: gen_large_mask(prng, h, w, **settings["256train"])
|
||||
make_narrow_lama_mask = lambda prng, h, w: gen_large_mask(prng, h, w, **settings["256narrow"])
|
||||
make_512_lama_mask = lambda prng, h, w: gen_large_mask(prng, h, w, **settings["512train"])
|
||||
make_512_lama_mask_large = lambda prng, h, w: gen_large_mask(prng, h, w, **settings["512train-large"])
|
||||
|
||||
make_narrow_lama_mask = lambda prng, h, w: gen_large_mask(prng, h, w,
|
||||
**settings["256narrow"])
|
||||
|
||||
make_512_lama_mask = lambda prng, h, w: gen_large_mask(prng, h, w,
|
||||
**settings["512train"])
|
||||
MASK_MODES = {
|
||||
"256train": make_lama_mask,
|
||||
"256narrow": make_narrow_lama_mask,
|
||||
"512train": make_512_lama_mask,
|
||||
"512train-large": make_512_lama_mask_large
|
||||
}
|
||||
|
||||
if __name__ == "__main__":
|
||||
import sys
|
||||
|
|
|
|||
|
|
@ -16,7 +16,7 @@ from webdataset.handlers import warn_and_continue
|
|||
|
||||
|
||||
from ldm.util import instantiate_from_config
|
||||
from ldm.data.inpainting.synthetic_mask import gen_large_mask, make_lama_mask, make_narrow_lama_mask, make_512_lama_mask
|
||||
from ldm.data.inpainting.synthetic_mask import gen_large_mask, MASK_MODES
|
||||
from ldm.data.base import PRNGMixin
|
||||
|
||||
|
||||
|
|
@ -232,9 +232,10 @@ class AddLR(object):
|
|||
|
||||
|
||||
class AddMask(PRNGMixin):
|
||||
def __init__(self, size=512):
|
||||
def __init__(self, mode="512train"):
|
||||
super().__init__()
|
||||
self.make_mask = make_512_lama_mask if size == 512 else make_lama_mask
|
||||
assert mode in list(MASK_MODES.keys()), f'unknown mask generation mode "{mode}"'
|
||||
self.make_mask = MASK_MODES[mode]
|
||||
|
||||
def __call__(self, sample):
|
||||
# sample['jpg'] is tensor hwc in [-1, 1] at this point
|
||||
|
|
|
|||
|
|
@ -1487,9 +1487,10 @@ class LatentUpscaleDiffusion(LatentDiffusion):
|
|||
x_low = x_low.to(memory_format=torch.contiguous_format).float()
|
||||
zx, noise_level = self.low_scale_model(x_low)
|
||||
all_conds = {"c_concat": [zx], "c_crossattn": [c], "c_adm": noise_level}
|
||||
#import pudb; pu.db
|
||||
if log_mode:
|
||||
# TODO: maybe disable if too expensive
|
||||
interpretability = True
|
||||
interpretability = False
|
||||
if interpretability:
|
||||
zx = zx[:, :, ::2, ::2]
|
||||
x_low_rec = self.low_scale_model.decode(zx)
|
||||
|
|
@ -1567,13 +1568,13 @@ class LatentUpscaleDiffusion(LatentDiffusion):
|
|||
if k == "c_crossattn":
|
||||
assert isinstance(c[k], list) and len(c[k]) == 1
|
||||
uc[k] = [uc_tmp]
|
||||
elif k == "c_adm":
|
||||
elif k == "c_adm": # todo: only run with text-based guidance?
|
||||
assert isinstance(c[k], torch.Tensor)
|
||||
uc[k] = torch.ones_like(c[k]) * (self.low_scale_model.max_noise_level-1)
|
||||
uc[k] = torch.ones_like(c[k]) * self.low_scale_model.max_noise_level
|
||||
elif isinstance(c[k], list):
|
||||
uc[k] = [torch.zeros_like(c[k][i]) for i in range(len(c[k]))]
|
||||
uc[k] = [c[k][i] for i in range(len(c[k]))]
|
||||
else:
|
||||
uc[k] = torch.zeros_like(c[k])
|
||||
uc[k] = c[k]
|
||||
|
||||
with ema_scope("Sampling with classifier-free guidance"):
|
||||
samples_cfg, _ = self.sample_log(cond=c, batch_size=N, ddim=use_ddim,
|
||||
|
|
@ -1642,8 +1643,7 @@ class LatentInpaintDiffusion(LatentDiffusion):
|
|||
new_entry[:, :self.keep_dims, ...] = sd[k]
|
||||
sd[k] = new_entry
|
||||
|
||||
missing, unexpected = self.load_state_dict(sd, strict=False) if not only_model else self.model.load_state_dict(
|
||||
sd, strict=False)
|
||||
missing, unexpected = self.load_state_dict(sd, strict=False) if not only_model else self.model.load_state_dict(sd, strict=False)
|
||||
print(f"Restored from {path} with {len(missing)} missing and {len(unexpected)} unexpected keys")
|
||||
if len(missing) > 0:
|
||||
print(f"Missing Keys: {missing}")
|
||||
|
|
|
|||
|
|
@ -255,8 +255,9 @@ class LowScaleEncoder(nn.Module):
|
|||
z = z * self.scale_factor
|
||||
noise_level = torch.randint(0, self.max_noise_level, (x.shape[0],), device=x.device).long()
|
||||
z = self.q_sample(z, noise_level)
|
||||
#z = torch.nn.functional.interpolate(z, size=self.out_size, mode="nearest") # TODO: experiment with mode
|
||||
z = z.repeat_interleave(2, -2).repeat_interleave(2, -1)
|
||||
if self.out_size is not None:
|
||||
z = torch.nn.functional.interpolate(z, size=self.out_size, mode="nearest") # TODO: experiment with mode
|
||||
# z = z.repeat_interleave(2, -2).repeat_interleave(2, -1)
|
||||
return z, noise_level
|
||||
|
||||
def decode(self, z):
|
||||
|
|
|
|||
|
|
@ -0,0 +1,27 @@
|
|||
#!/bin/bash
|
||||
|
||||
# mpi version for node rank
|
||||
H=`hostname`
|
||||
THEID=`echo -e $HOSTNAMES | python3 -c "import sys;[sys.stdout.write(str(i)) for i,line in enumerate(next(sys.stdin).split(' ')) if line.strip() == '$H'.strip()]"`
|
||||
export NODE_RANK=${THEID}
|
||||
echo THEID=$THEID
|
||||
|
||||
echo "##########################################"
|
||||
echo MASTER_ADDR=${MASTER_ADDR}
|
||||
echo MASTER_PORT=${MASTER_PORT}
|
||||
echo NODE_RANK=${NODE_RANK}
|
||||
echo WORLD_SIZE=${WORLD_SIZE}
|
||||
echo "##########################################"
|
||||
# debug environment worked great so we stick with it
|
||||
# no magic there, just a miniconda python=3.9, pytorch=1.12, cudatoolkit=11.3
|
||||
# env with pip dependencies from stable diffusion's requirements.txt
|
||||
eval "$(/fsx/stable-diffusion/debug/miniconda3/bin/conda shell.bash hook)"
|
||||
conda activate torch111
|
||||
cd /fsx/robin/stable-diffusion/stable-diffusion
|
||||
|
||||
CONFIG="/fsx/robin/stable-diffusion/stable-diffusion/configs/stable-diffusion/upscaling/upscale-v1-with-f16.yaml"
|
||||
|
||||
# debugging
|
||||
#EXTRA="${EXTRA} -d True lightning.callbacks.image_logger.params.batch_frequency=50"
|
||||
|
||||
python main.py --base $CONFIG --gpus 0,1,2,3,4,5,6,7 -t --num_nodes ${WORLD_SIZE} --scale_lr False #$EXTRA
|
||||
|
|
@ -0,0 +1,42 @@
|
|||
#!/bin/bash
|
||||
#SBATCH --partition=compute-od-gpu
|
||||
#SBATCH --job-name=stable-diffusion-v1-upscaling-f16-pretraining-512-aesthetics
|
||||
#SBATCH --nodes 8
|
||||
#SBATCH --ntasks-per-node 1
|
||||
#SBATCH --cpus-per-gpu=4
|
||||
#SBATCH --gres=gpu:8
|
||||
#SBATCH --exclusive
|
||||
#SBATCH --output=%x_%j.out
|
||||
#SBATCH --comment "Key=Monitoring,Value=ON"
|
||||
|
||||
module load intelmpi
|
||||
source /opt/intel/mpi/latest/env/vars.sh
|
||||
export LD_LIBRARY_PATH=/opt/aws-ofi-nccl/lib:/opt/amazon/efa/lib64:/usr/local/cuda-11.0/efa/lib:/usr/local/cuda-11.0/lib:/usr/local/cuda-11.0/lib64:/usr/local/cuda-11.0:/opt/nccl/build/lib:/opt/aws-ofi-nccl-inst
|
||||
all/lib:/opt/aws-ofi-nccl/lib:$LD_LIBRARY_PATH
|
||||
export NCCL_PROTO=simple
|
||||
export PATH=/opt/amazon/efa/bin:$PATH
|
||||
export LD_PRELOAD="/opt/nccl/build/lib/libnccl.so"
|
||||
export FI_EFA_FORK_SAFE=1
|
||||
export FI_LOG_LEVEL=1
|
||||
export FI_EFA_USE_DEVICE_RDMA=1 # use for p4dn
|
||||
export NCCL_DEBUG=info
|
||||
export PYTHONFAULTHANDLER=1
|
||||
export CUDA_LAUNCH_BLOCKING=0
|
||||
export OMPI_MCA_mtl_base_verbose=1
|
||||
export FI_EFA_ENABLE_SHM_TRANSFER=0
|
||||
export FI_PROVIDER=efa
|
||||
export FI_EFA_TX_MIN_CREDITS=64
|
||||
export NCCL_TREE_THRESHOLD=0
|
||||
|
||||
# sent to sub script
|
||||
export HOSTNAMES=`scontrol show hostnames "$SLURM_JOB_NODELIST"`
|
||||
export MASTER_ADDR=$(scontrol show hostnames "$SLURM_JOB_NODELIST" | head -n 1)
|
||||
export MASTER_PORT=12802
|
||||
export COUNT_NODE=`scontrol show hostnames "$SLURM_JOB_NODELIST" | wc -l`
|
||||
export WORLD_SIZE=$COUNT_NODE
|
||||
|
||||
echo go $COUNT_NODE
|
||||
echo $HOSTNAMES
|
||||
echo $WORLD_SIZE
|
||||
|
||||
mpirun -n $COUNT_NODE -perhost 1 /fsx/robin/stable-diffusion/stable-diffusion/scripts/slurm/v1-upscaling-f16-pretraining-512-aesthetics/launcher.sh
|
||||
|
|
@ -0,0 +1,27 @@
|
|||
#!/bin/bash
|
||||
|
||||
# mpi version for node rank
|
||||
H=`hostname`
|
||||
THEID=`echo -e $HOSTNAMES | python3 -c "import sys;[sys.stdout.write(str(i)) for i,line in enumerate(next(sys.stdin).split(' ')) if line.strip() == '$H'.strip()]"`
|
||||
export NODE_RANK=${THEID}
|
||||
echo THEID=$THEID
|
||||
|
||||
echo "##########################################"
|
||||
echo MASTER_ADDR=${MASTER_ADDR}
|
||||
echo MASTER_PORT=${MASTER_PORT}
|
||||
echo NODE_RANK=${NODE_RANK}
|
||||
echo WORLD_SIZE=${WORLD_SIZE}
|
||||
echo "##########################################"
|
||||
# debug environment worked great so we stick with it
|
||||
# no magic there, just a miniconda python=3.9, pytorch=1.12, cudatoolkit=11.3
|
||||
# env with pip dependencies from stable diffusion's requirements.txt
|
||||
eval "$(/fsx/stable-diffusion/debug/miniconda3/bin/conda shell.bash hook)"
|
||||
conda activate torch111
|
||||
cd /fsx/robin/stable-diffusion/stable-diffusion
|
||||
|
||||
CONFIG="/fsx/robin/stable-diffusion/stable-diffusion/configs/stable-diffusion/inpainting/v1-finetune-for-inpainting-laion-aesthetic-larger-masks.yaml"
|
||||
|
||||
# debugging
|
||||
#EXTRA="${EXTRA} -d True lightning.callbacks.image_logger.params.batch_frequency=50"
|
||||
|
||||
python main.py --base $CONFIG --gpus 0,1,2,3,4,5,6,7 -t --num_nodes ${WORLD_SIZE} --scale_lr False
|
||||
|
|
@ -0,0 +1,42 @@
|
|||
#!/bin/bash
|
||||
#SBATCH --partition=compute-od-gpu
|
||||
#SBATCH --job-name=stable-diffusion-v1-v1_inpainting_aesthetics-larger-masks
|
||||
#SBATCH --nodes 24
|
||||
#SBATCH --ntasks-per-node 1
|
||||
#SBATCH --cpus-per-gpu=4
|
||||
#SBATCH --gres=gpu:8
|
||||
#SBATCH --exclusive
|
||||
#SBATCH --output=%x_%j.out
|
||||
#SBATCH --comment "Key=Monitoring,Value=ON"
|
||||
|
||||
module load intelmpi
|
||||
source /opt/intel/mpi/latest/env/vars.sh
|
||||
export LD_LIBRARY_PATH=/opt/aws-ofi-nccl/lib:/opt/amazon/efa/lib64:/usr/local/cuda-11.0/efa/lib:/usr/local/cuda-11.0/lib:/usr/local/cuda-11.0/lib64:/usr/local/cuda-11.0:/opt/nccl/build/lib:/opt/aws-ofi-nccl-inst
|
||||
all/lib:/opt/aws-ofi-nccl/lib:$LD_LIBRARY_PATH
|
||||
export NCCL_PROTO=simple
|
||||
export PATH=/opt/amazon/efa/bin:$PATH
|
||||
export LD_PRELOAD="/opt/nccl/build/lib/libnccl.so"
|
||||
export FI_EFA_FORK_SAFE=1
|
||||
export FI_LOG_LEVEL=1
|
||||
export FI_EFA_USE_DEVICE_RDMA=1 # use for p4dn
|
||||
export NCCL_DEBUG=info
|
||||
export PYTHONFAULTHANDLER=1
|
||||
export CUDA_LAUNCH_BLOCKING=0
|
||||
export OMPI_MCA_mtl_base_verbose=1
|
||||
export FI_EFA_ENABLE_SHM_TRANSFER=0
|
||||
export FI_PROVIDER=efa
|
||||
export FI_EFA_TX_MIN_CREDITS=64
|
||||
export NCCL_TREE_THRESHOLD=0
|
||||
|
||||
# sent to sub script
|
||||
export HOSTNAMES=`scontrol show hostnames "$SLURM_JOB_NODELIST"`
|
||||
export MASTER_ADDR=$(scontrol show hostnames "$SLURM_JOB_NODELIST" | head -n 1)
|
||||
export MASTER_PORT=12802
|
||||
export COUNT_NODE=`scontrol show hostnames "$SLURM_JOB_NODELIST" | wc -l`
|
||||
export WORLD_SIZE=$COUNT_NODE
|
||||
|
||||
echo go $COUNT_NODE
|
||||
echo $HOSTNAMES
|
||||
echo $WORLD_SIZE
|
||||
|
||||
mpirun -n $COUNT_NODE -perhost 1 /fsx/robin/stable-diffusion/stable-diffusion/scripts/slurm/v1_inpainting_aesthetics-larger-masks/launcher.sh
|
||||
Loading…
Reference in New Issue