diffusers
/

shot-categorizer-v0

Model card Files Files and versions

sayakpaul HF Staff commited on Mar 4

Commit

a1da087

·

verified ·

1 Parent(s): d9b7396

Update README.md

Files changed (1) hide show

README.md +4 -3

README.md CHANGED Viewed

@@ -24,7 +24,8 @@ Training configuration:
 * Hardware: 8xH100s
 Training was conducted using FP16 mixed-precision and DeepSpeed Zero2 scheme. The vision tower of the model
-was kept frozen during the training.
 ## Inference
@@ -35,7 +36,7 @@ from PIL import Image
 import requests
-folder_path = "diffusers-internal-dev/shot-categorizer-v0"
 model = (
     AutoModelForCausalLM.from_pretrained(folder_path, torch_dtype=torch.float16, trust_remote_code=True)
     .to("cuda")
@@ -44,7 +45,7 @@ model = (
 processor = AutoProcessor.from_pretrained(folder_path, trust_remote_code=True)
 prompts = ["<COLOR>", "<LIGHTING>", "<LIGHTING_TYPE>", "<COMPOSITION>"]
-url = "diffusers-internal-dev/shot-categorizer-v0/resolve/main/assets/image_3.jpg"
 image = Image.open(img_path).convert("RGB")
 with torch.no_grad() and torch.inference_mode():

 * Hardware: 8xH100s
 Training was conducted using FP16 mixed-precision and DeepSpeed Zero2 scheme. The vision tower of the model
+was kept frozen during the training. We used the [diffusers/ShotDEAD-v0](https://huggingface.co/datasets/diffusers/ShotDEAD-v0)
+dataset for conducting training.
 ## Inference
 import requests
+folder_path = "diffusers/shot-categorizer-v0"
 model = (
     AutoModelForCausalLM.from_pretrained(folder_path, torch_dtype=torch.float16, trust_remote_code=True)
     .to("cuda")
 processor = AutoProcessor.from_pretrained(folder_path, trust_remote_code=True)
 prompts = ["<COLOR>", "<LIGHTING>", "<LIGHTING_TYPE>", "<COMPOSITION>"]
+img_path = "./assets/image_3.jpg"
 image = Image.open(img_path).convert("RGB")
 with torch.no_grad() and torch.inference_mode():