Instructions to use Angel-cell/ProGraph with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Angel-cell/ProGraph with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Angel-cell/ProGraph", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Yanggenfan commited on
Upload 2 files
Browse files
models/hrnet/cls_hrnet_w64_sgd_lr5e-2_wd1e-4_bs32_x100.yaml
ADDED
|
@@ -0,0 +1,92 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
GPUS: (0,1,2,3)
|
| 2 |
+
LOG_DIR: 'log/'
|
| 3 |
+
DATA_DIR: ''
|
| 4 |
+
OUTPUT_DIR: 'output/'
|
| 5 |
+
WORKERS: 4
|
| 6 |
+
PRINT_FREQ: 1000
|
| 7 |
+
|
| 8 |
+
MODEL:
|
| 9 |
+
NAME: cls_hrnet
|
| 10 |
+
IMAGE_SIZE:
|
| 11 |
+
- 224
|
| 12 |
+
- 224
|
| 13 |
+
EXTRA:
|
| 14 |
+
STAGE1:
|
| 15 |
+
NUM_MODULES: 1
|
| 16 |
+
NUM_RANCHES: 1
|
| 17 |
+
BLOCK: BOTTLENECK
|
| 18 |
+
NUM_BLOCKS:
|
| 19 |
+
- 4
|
| 20 |
+
NUM_CHANNELS:
|
| 21 |
+
- 64
|
| 22 |
+
FUSE_METHOD: SUM
|
| 23 |
+
STAGE2:
|
| 24 |
+
NUM_MODULES: 1
|
| 25 |
+
NUM_BRANCHES: 2
|
| 26 |
+
BLOCK: BASIC
|
| 27 |
+
NUM_BLOCKS:
|
| 28 |
+
- 4
|
| 29 |
+
- 4
|
| 30 |
+
NUM_CHANNELS:
|
| 31 |
+
- 64
|
| 32 |
+
- 128
|
| 33 |
+
FUSE_METHOD: SUM
|
| 34 |
+
STAGE3:
|
| 35 |
+
NUM_MODULES: 4
|
| 36 |
+
NUM_BRANCHES: 3
|
| 37 |
+
BLOCK: BASIC
|
| 38 |
+
NUM_BLOCKS:
|
| 39 |
+
- 4
|
| 40 |
+
- 4
|
| 41 |
+
- 4
|
| 42 |
+
NUM_CHANNELS:
|
| 43 |
+
- 64
|
| 44 |
+
- 128
|
| 45 |
+
- 256
|
| 46 |
+
FUSE_METHOD: SUM
|
| 47 |
+
STAGE4:
|
| 48 |
+
NUM_MODULES: 3
|
| 49 |
+
NUM_BRANCHES: 4
|
| 50 |
+
BLOCK: BASIC
|
| 51 |
+
NUM_BLOCKS:
|
| 52 |
+
- 4
|
| 53 |
+
- 4
|
| 54 |
+
- 4
|
| 55 |
+
- 4
|
| 56 |
+
NUM_CHANNELS:
|
| 57 |
+
- 64
|
| 58 |
+
- 128
|
| 59 |
+
- 256
|
| 60 |
+
- 512
|
| 61 |
+
FUSE_METHOD: SUM
|
| 62 |
+
CUDNN:
|
| 63 |
+
BENCHMARK: true
|
| 64 |
+
DETERMINISTIC: false
|
| 65 |
+
ENABLED: true
|
| 66 |
+
DATASET:
|
| 67 |
+
DATASET: 'imagenet'
|
| 68 |
+
DATA_FORMAT: 'jpg'
|
| 69 |
+
ROOT: 'data/imagenet/'
|
| 70 |
+
TEST_SET: 'val'
|
| 71 |
+
TRAIN_SET: 'train'
|
| 72 |
+
TEST:
|
| 73 |
+
BATCH_SIZE_PER_GPU: 32
|
| 74 |
+
MODEL_FILE: ''
|
| 75 |
+
TRAIN:
|
| 76 |
+
BATCH_SIZE_PER_GPU: 32
|
| 77 |
+
BEGIN_EPOCH: 0
|
| 78 |
+
END_EPOCH: 100
|
| 79 |
+
RESUME: true
|
| 80 |
+
LR_FACTOR: 0.1
|
| 81 |
+
LR_STEP:
|
| 82 |
+
- 30
|
| 83 |
+
- 60
|
| 84 |
+
- 90
|
| 85 |
+
OPTIMIZER: sgd
|
| 86 |
+
LR: 0.05
|
| 87 |
+
WD: 0.0001
|
| 88 |
+
MOMENTUM: 0.9
|
| 89 |
+
NESTEROV: true
|
| 90 |
+
SHUFFLE: true
|
| 91 |
+
DEBUG:
|
| 92 |
+
DEBUG: false
|
models/hrnet/hrnetv2_w64_imagenet_pretrained.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41ed675bcd1f4f4b62a49bad64901f08f8b67ed744b715da87738f926dae685c
|
| 3 |
+
size 513111608
|