github/ColossalAI
1
0
Fork 0
mirror of https://github.com/hpcaitech/ColossalAI.git synced 2025-09-01 17:17:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

[misc] update pre-commit and run all files (#4752)

Browse Source 
* [misc] update pre-commit

* [misc] run pre-commit

* [misc] remove useless configuration files

* [misc] ignore cuda for clang-format
This commit is contained in:
Hongxin Liu
2023-09-19 14:20:26 +08:00
committed by GitHub
parent 3c6b831c26
commit 079bf3cb26
1268 changed files with 50037 additions and 38444 deletions
Download Patch File Download Diff File Expand all files Collapse all files

104
examples/images/diffusion/ldm/modules/encoders/modules.py
View File

@@ -1,11 +1,9 @@
import open_clip
import torch
import torch.nn as nn
from ldm.util import count_params
from torch.utils.checkpoint import checkpoint
from transformers import T5Tokenizer, T5EncoderModel, CLIPTokenizer, CLIPTextModel
import open_clip
from ldm.util import default, count_params
from transformers import CLIPTextModel, CLIPTokenizer, T5EncoderModel, T5Tokenizer
class AbstractEncoder(nn.Module):
@@ -17,13 +15,12 @@ class AbstractEncoder(nn.Module):
class IdentityEncoder(AbstractEncoder):
def encode(self, x):
return x
class ClassEmbedder(nn.Module):
def __init__(self, embed_dim, n_classes=1000, key='class', ucg_rate=0.1):
def __init__(self, embed_dim, n_classes=1000, key="class", ucg_rate=0.1):
super().__init__()
self.key = key
self.embedding = nn.Embedding(n_classes, embed_dim)
@@ -35,9 +32,9 @@ class ClassEmbedder(nn.Module):
key = self.key
# this is for use in crossattn
c = batch[key][:, None]
if self.ucg_rate > 0. and not disable_dropout:
mask = 1. - torch.bernoulli(torch.ones_like(c) * self.ucg_rate)
c = mask * c + (1-mask) * torch.ones_like(c)*(self.n_classes-1)
if self.ucg_rate > 0.0 and not disable_dropout:
mask = 1.0 - torch.bernoulli(torch.ones_like(c) * self.ucg_rate)
c = mask * c + (1 - mask) * torch.ones_like(c) * (self.n_classes - 1)
c = c.long()
c = self.embedding(c)
return c
@@ -57,24 +54,34 @@ def disabled_train(self, mode=True):
class FrozenT5Embedder(AbstractEncoder):
"""Uses the T5 transformer encoder for text"""
def __init__(self, version="google/t5-v1_1-large", device="cuda", max_length=77, freeze=True): # others are google/t5-v1_1-xl and google/t5-v1_1-xxl
def __init__(
self, version="google/t5-v1_1-large", device="cuda", max_length=77, freeze=True
): # others are google/t5-v1_1-xl and google/t5-v1_1-xxl
super().__init__()
self.tokenizer = T5Tokenizer.from_pretrained(version)
self.transformer = T5EncoderModel.from_pretrained(version)
self.device = device
self.max_length = max_length # TODO: typical value?
self.max_length = max_length # TODO: typical value?
if freeze:
self.freeze()
def freeze(self):
self.transformer = self.transformer.eval()
#self.train = disabled_train
# self.train = disabled_train
for param in self.parameters():
param.requires_grad = False
def forward(self, text):
batch_encoding = self.tokenizer(text, truncation=True, max_length=self.max_length, return_length=True,
return_overflowing_tokens=False, padding="max_length", return_tensors="pt")
batch_encoding = self.tokenizer(
text,
truncation=True,
max_length=self.max_length,
return_length=True,
return_overflowing_tokens=False,
padding="max_length",
return_tensors="pt",
)
tokens = batch_encoding["input_ids"].to(self.device)
outputs = self.transformer(input_ids=tokens)
@@ -87,13 +94,18 @@ class FrozenT5Embedder(AbstractEncoder):
class FrozenCLIPEmbedder(AbstractEncoder):
"""Uses the CLIP transformer encoder for text (from huggingface)"""
LAYERS = [
"last",
"pooled",
"hidden"
]
def __init__(self, version="openai/clip-vit-large-patch14", device="cuda", max_length=77,
freeze=True, layer="last", layer_idx=None): # clip-vit-base-patch32
LAYERS = ["last", "pooled", "hidden"]
def __init__(
self,
version="openai/clip-vit-large-patch14",
device="cuda",
max_length=77,
freeze=True,
layer="last",
layer_idx=None,
): # clip-vit-base-patch32
super().__init__()
assert layer in self.LAYERS
self.tokenizer = CLIPTokenizer.from_pretrained(version)
@@ -110,15 +122,22 @@ class FrozenCLIPEmbedder(AbstractEncoder):
def freeze(self):
self.transformer = self.transformer.eval()
#self.train = disabled_train
# self.train = disabled_train
for param in self.parameters():
param.requires_grad = False
def forward(self, text):
batch_encoding = self.tokenizer(text, truncation=True, max_length=self.max_length, return_length=True,
return_overflowing_tokens=False, padding="max_length", return_tensors="pt")
batch_encoding = self.tokenizer(
text,
truncation=True,
max_length=self.max_length,
return_length=True,
return_overflowing_tokens=False,
padding="max_length",
return_tensors="pt",
)
tokens = batch_encoding["input_ids"].to(self.device)
outputs = self.transformer(input_ids=tokens, output_hidden_states=self.layer=="hidden")
outputs = self.transformer(input_ids=tokens, output_hidden_states=self.layer == "hidden")
if self.layer == "last":
z = outputs.last_hidden_state
elif self.layer == "pooled":
@@ -135,16 +154,19 @@ class FrozenOpenCLIPEmbedder(AbstractEncoder):
"""
Uses the OpenCLIP transformer encoder for text
"""
LAYERS = [
#"pooled",
# "pooled",
"last",
"penultimate"
"penultimate",
]
def __init__(self, arch="ViT-H-14", version="laion2b_s32b_b79k", device="cuda", max_length=77,
freeze=True, layer="last"):
def __init__(
self, arch="ViT-H-14", version="laion2b_s32b_b79k", device="cuda", max_length=77, freeze=True, layer="last"
):
super().__init__()
assert layer in self.LAYERS
model, _, _ = open_clip.create_model_and_transforms(arch, device=torch.device('cpu'), pretrained=version)
model, _, _ = open_clip.create_model_and_transforms(arch, device=torch.device("cpu"), pretrained=version)
del model.visual
self.model = model
@@ -179,7 +201,7 @@ class FrozenOpenCLIPEmbedder(AbstractEncoder):
x = self.model.ln_final(x)
return x
def text_transformer_forward(self, x: torch.Tensor, attn_mask = None):
def text_transformer_forward(self, x: torch.Tensor, attn_mask=None):
for i, r in enumerate(self.model.transformer.resblocks):
if i == len(self.model.transformer.resblocks) - self.layer_idx:
break
@@ -194,13 +216,21 @@ class FrozenOpenCLIPEmbedder(AbstractEncoder):
class FrozenCLIPT5Encoder(AbstractEncoder):
def __init__(self, clip_version="openai/clip-vit-large-patch14", t5_version="google/t5-v1_1-xl", device="cuda",
clip_max_length=77, t5_max_length=77):
def __init__(
self,
clip_version="openai/clip-vit-large-patch14",
t5_version="google/t5-v1_1-xl",
device="cuda",
clip_max_length=77,
t5_max_length=77,
):
super().__init__()
self.clip_encoder = FrozenCLIPEmbedder(clip_version, device, max_length=clip_max_length)
self.t5_encoder = FrozenT5Embedder(t5_version, device, max_length=t5_max_length)
print(f"{self.clip_encoder.__class__.__name__} has {count_params(self.clip_encoder)*1.e-6:.2f} M parameters, "
f"{self.t5_encoder.__class__.__name__} comes with {count_params(self.t5_encoder)*1.e-6:.2f} M params.")
print(
f"{self.clip_encoder.__class__.__name__} has {count_params(self.clip_encoder)*1.e-6:.2f} M parameters, "
f"{self.t5_encoder.__class__.__name__} comes with {count_params(self.t5_encoder)*1.e-6:.2f} M params."
)
def encode(self, text):
return self(text)
@@ -209,5 +239,3 @@ class FrozenCLIPT5Encoder(AbstractEncoder):
clip_z = self.clip_encoder.encode(text)
t5_z = self.t5_encoder.encode(text)
return [clip_z, t5_z]