Merge remote-tracking branch 'origin/main'

shreyazomato · Aug 3, 2022 · a166aa7 · a166aa7
2 parents 51cd488 + ea8034d
commit a166aa7
Show file tree

Hide file tree

Showing 5 changed files with 236 additions and 4 deletions.
diff --git a/...iffusion/inpainting/v1-finetune-for-inpainting-laion-aesthetic-larger-masks-and-ucfg.yaml b/...iffusion/inpainting/v1-finetune-for-inpainting-laion-aesthetic-larger-masks-and-ucfg.yaml
@@ -0,0 +1,156 @@
+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/v1pphrflatlined2-pruned.ckpt"
+
+    ucg_training:
+      txt:
+        p: 0.1
+        val: ""
+
+    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"
+          p_drop: 0.25
+
+    # 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"
+          p_drop: 0.25
+
+
+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
diff --git a/ldm/data/laion.py b/ldm/data/laion.py
@@ -242,15 +242,18 @@ def __call__(self, sample):
 
 
 class AddMask(PRNGMixin):
-    def __init__(self, mode="512train"):
+    def __init__(self, mode="512train", p_drop=0.):
         super().__init__()
         assert mode in list(MASK_MODES.keys()), f'unknown mask generation mode "{mode}"'
         self.make_mask = MASK_MODES[mode]
+        self.p_drop = p_drop
 
     def __call__(self, sample):
         # sample['jpg'] is tensor hwc in [-1, 1] at this point
         x = sample['jpg']
         mask = self.make_mask(self.prng, x.shape[0], x.shape[1])
+        if self.prng.choice(2, p=[1 - self.p_drop, self.p_drop]):
+            mask = np.ones_like(mask)
         mask[mask < 0.5] = 0
         mask[mask > 0.5] = 1
         mask = torch.from_numpy(mask[..., None])

diff --git a/ldm/models/diffusion/ddpm.py b/ldm/models/diffusion/ddpm.py
@@ -122,7 +122,6 @@ def __init__(self,
         if self.ucg_training:
             self.ucg_prng = np.random.RandomState()
 
-
     def register_schedule(self, given_betas=None, beta_schedule="linear", timesteps=1000,
                           linear_start=1e-4, linear_end=2e-2, cosine_s=8e-3):
         if exists(given_betas):
@@ -1603,7 +1602,9 @@ class LatentInpaintDiffusion(LatentDiffusion):
     To disable finetuning mode, set finetune_keys to None
      """
     def __init__(self,
-                 finetune_keys=("model.diffusion_model.input_blocks.0.0.weight", "model_ema.diffusion_modelinput_blocks00weight"),
+                 finetune_keys=("model.diffusion_model.input_blocks.0.0.weight",
+                                "model_ema.diffusion_modelinput_blocks00weight"
+                                ),
                  concat_keys=("mask", "masked_image"),
                  masked_image_key="masked_image",
                  keep_finetune_dims=4,  # if model was trained without concat mode before and we would like to keep these channels
@@ -1657,7 +1658,7 @@ def init_from_ckpt(self, path, ignore_keys=list(), only_model=False):
     @torch.no_grad()
     def get_input(self, batch, k, cond_key=None, bs=None, return_first_stage_outputs=False):
         # note: restricted to non-trainable encoders currently
-        assert not self.cond_stage_trainable, 'trainable cond stages not yet supported for inpaiting'
+        assert not self.cond_stage_trainable, 'trainable cond stages not yet supported for inpainting'
         z, c, x, xrec, xc = super().get_input(batch, self.first_stage_key, return_first_stage_outputs=True,
                                               force_c_encode=True, return_original_cond=True, bs=bs)
 

diff --git a/scripts/slurm/v1_inpainting_aesthetics-larger-masks-ucg/launcher.sh b/scripts/slurm/v1_inpainting_aesthetics-larger-masks-ucg/launcher.sh
@@ -0,0 +1,30 @@
+#!/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 "$(/fsx/stable-diffusion/debug/miniconda3/bin/conda shell.bash hook)"
+conda activate stable
+cd /fsx/robin/stable-diffusion/stable-diffusion
+
+CONFIG="/fsx/robin/stable-diffusion/stable-diffusion/configs/stable-diffusion/inpainting/v1-finetune-for-inpainting-laion-aesthetic-larger-masks-and-ucfg.yaml"
+
+# debugging
+#EXTRA="${EXTRA} -d True lightning.callbacks.image_logger.params.batch_frequency=50"
+
+# detect bad gpus early on
+/bin/bash /fsx/stable-diffusion/stable-diffusion/scripts/test_gpu.sh
+
+python main.py --base $CONFIG --gpus 0,1,2,3,4,5,6,7 -t --num_nodes ${WORLD_SIZE} --scale_lr False
diff --git a/scripts/slurm/v1_inpainting_aesthetics-larger-masks-ucg/sbatch.sh b/scripts/slurm/v1_inpainting_aesthetics-larger-masks-ucg/sbatch.sh
@@ -0,0 +1,42 @@
+#!/bin/bash
+#SBATCH --partition=compute-od-gpu
+#SBATCH --job-name=stable-diffusion-v1-v1_inpainting_aesthetics-larger-masks
+#SBATCH --nodes 32
+#SBATCH --ntasks-per-node 1
+#SBATCH --cpus-per-gpu=4
+#SBATCH --gres=gpu:8
+#SBATCH --exclusive
+#SBATCH --output=%x_%j.out
+#SBATCH --comment "Key=Monitoring,Value=ON"
+
+module load intelmpi
+source /opt/intel/mpi/latest/env/vars.sh
+export LD_LIBRARY_PATH=/opt/aws-ofi-nccl/lib:/opt/amazon/efa/lib64:/usr/local/cuda-11.0/efa/lib:/usr/local/cuda-11.0/lib:/usr/local/cuda-11.0/lib64:/usr/local/cuda-11.0:/opt/nccl/build/lib:/opt/aws-ofi-nccl-inst
+all/lib:/opt/aws-ofi-nccl/lib:$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-ucg/launcher.sh