Muhammad Taqi Raza
commited on
Commit
·
15db18d
1
Parent(s):
8e3cdd5
adding estimate near_far
Browse files- gradio_app.py +7 -170
- inference/v2v_data/models/infer.py +9 -0
gradio_app.py
CHANGED
@@ -1,179 +1,10 @@
|
|
1 |
-
# import os
|
2 |
-
# import subprocess
|
3 |
-
# from datetime import datetime
|
4 |
-
# from pathlib import Path
|
5 |
-
# import gradio as gr
|
6 |
-
|
7 |
-
# # -----------------------------
|
8 |
-
# # Setup paths and env
|
9 |
-
# # -----------------------------
|
10 |
-
# HF_HOME = "/app/hf_cache"
|
11 |
-
# os.environ["HF_HOME"] = HF_HOME
|
12 |
-
# os.environ["TRANSFORMERS_CACHE"] = HF_HOME
|
13 |
-
# os.makedirs(HF_HOME, exist_ok=True)
|
14 |
-
|
15 |
-
# PRETRAINED_DIR = "/app/pretrained"
|
16 |
-
# os.makedirs(PRETRAINED_DIR, exist_ok=True)
|
17 |
-
|
18 |
-
|
19 |
-
# # -----------------------------
|
20 |
-
# # Step 1: Optional Model Download
|
21 |
-
# # -----------------------------
|
22 |
-
# def download_models():
|
23 |
-
# expected_model = os.path.join(PRETRAINED_DIR, "RAFT/raft-things.pth")
|
24 |
-
# if not Path(expected_model).exists():
|
25 |
-
# print("⚙️ Downloading pretrained models...")
|
26 |
-
# try:
|
27 |
-
# subprocess.check_call(["bash", "download/download_models.sh"])
|
28 |
-
# print("✅ Models downloaded.")
|
29 |
-
# except subprocess.CalledProcessError as e:
|
30 |
-
# print(f"❌ Model download failed: {e}")
|
31 |
-
# else:
|
32 |
-
# print("✅ Pretrained models already exist.")
|
33 |
-
|
34 |
-
|
35 |
-
# download_models()
|
36 |
-
|
37 |
-
|
38 |
-
# # -----------------------------
|
39 |
-
# # Step 2: Inference Logic
|
40 |
-
# # -----------------------------
|
41 |
-
|
42 |
-
# def run_epic_inference(video_path, caption, motion_type):
|
43 |
-
# temp_input_path = "/app/temp_input.mp4"
|
44 |
-
# output_dir = f"/app/output_anchor"
|
45 |
-
# video_output_path = f"{output_dir}/masked_videos/output.mp4"
|
46 |
-
# traj_name = motion_type
|
47 |
-
# traj_txt = f"/app/inference/v2v_data/test/trajs/{traj_name}.txt"
|
48 |
-
# # Save uploaded video
|
49 |
-
# if video_path:
|
50 |
-
# os.system(f"cp '{video_path}' {temp_input_path}")
|
51 |
-
|
52 |
-
# command = [
|
53 |
-
# "python", "/app/inference/v2v_data/inference.py",
|
54 |
-
# "--video_path", temp_input_path,
|
55 |
-
# "--stride", "1",
|
56 |
-
# "--out_dir", output_dir,
|
57 |
-
# "--radius_scale", "1",
|
58 |
-
# "--camera", "target",
|
59 |
-
# "--mask",
|
60 |
-
# "--target_pose", "0", "30", "-0.6", "0", "0",
|
61 |
-
# "--traj_txt", traj_txt,
|
62 |
-
# "--save_name", "output",
|
63 |
-
# "--mode", "gradual",
|
64 |
-
# ]
|
65 |
-
|
66 |
-
# # Run inference command
|
67 |
-
# try:
|
68 |
-
# result = subprocess.run(command, capture_output=True, text=True, check=True)
|
69 |
-
# print("Getting Anchor Videos run successfully.")
|
70 |
-
# logs = result.stdout
|
71 |
-
# except subprocess.CalledProcessError as e:
|
72 |
-
# logs = f"❌ Inference failed:\n{e.stderr}"
|
73 |
-
# return logs, None
|
74 |
-
|
75 |
-
# # Locate the output video
|
76 |
-
# if video_output_path:
|
77 |
-
# return logs, str(video_output_path)
|
78 |
-
# else:
|
79 |
-
# return f"Inference succeeded but no output video found in {output_dir}", None
|
80 |
-
# def print_output_directory(out_dir):
|
81 |
-
# result = ""
|
82 |
-
# for root, dirs, files in os.walk(out_dir):
|
83 |
-
# level = root.replace(out_dir, '').count(os.sep)
|
84 |
-
# indent = ' ' * 4 * level
|
85 |
-
# result += f"{indent}{os.path.basename(root)}/"
|
86 |
-
# sub_indent = ' ' * 4 * (level + 1)
|
87 |
-
# for f in files:
|
88 |
-
# result += f"{sub_indent}{f}\n"
|
89 |
-
# return result
|
90 |
-
|
91 |
-
# def inference(video_path, caption, motion_type):
|
92 |
-
# logs, video_masked = run_epic_inference(video_path, caption, motion_type)
|
93 |
-
|
94 |
-
# MODEL_PATH="/app/pretrained/CogVideoX-5b-I2V"
|
95 |
-
|
96 |
-
# ckpt_steps=500
|
97 |
-
# ckpt_dir="/app/out/EPiC_pretrained"
|
98 |
-
# ckpt_file=f"checkpoint-{ckpt_steps}.pt"
|
99 |
-
# ckpt_path=f"{ckpt_dir}/{ckpt_file}"
|
100 |
-
|
101 |
-
# video_root_dir= f"/app/output_anchor"
|
102 |
-
# out_dir=f"/app/output"
|
103 |
-
|
104 |
-
# command = [
|
105 |
-
# "python", "/app/inference/cli_demo_camera_i2v_pcd.py",
|
106 |
-
# "--video_root_dir", video_root_dir,
|
107 |
-
# "--base_model_path", MODEL_PATH,
|
108 |
-
# "--controlnet_model_path", ckpt_path,
|
109 |
-
# "--output_path", out_dir,
|
110 |
-
# "--start_camera_idx", "0",
|
111 |
-
# "--end_camera_idx", "8",
|
112 |
-
# "--controlnet_weights", "1.0",
|
113 |
-
# "--controlnet_guidance_start", "0.0",
|
114 |
-
# "--controlnet_guidance_end", "0.4",
|
115 |
-
# "--controlnet_input_channels", "3",
|
116 |
-
# "--controlnet_transformer_num_attn_heads", "4",
|
117 |
-
# "--controlnet_transformer_attention_head_dim", "64",
|
118 |
-
# "--controlnet_transformer_out_proj_dim_factor", "64",
|
119 |
-
# "--controlnet_transformer_out_proj_dim_zero_init",
|
120 |
-
# "--vae_channels", "16",
|
121 |
-
# "--num_frames", "49",
|
122 |
-
# "--controlnet_transformer_num_layers", "8",
|
123 |
-
# "--infer_with_mask",
|
124 |
-
# "--pool_style", "max",
|
125 |
-
# "--seed", "43"
|
126 |
-
# ]
|
127 |
-
|
128 |
-
# # Run the command
|
129 |
-
# result = subprocess.run(command, capture_output=True, text=True)
|
130 |
-
# if result.returncode == 0:
|
131 |
-
# print("Inference completed successfully.")
|
132 |
-
# else:
|
133 |
-
# print(f"Error occurred during inference: {result.stderr}")
|
134 |
-
|
135 |
-
# # Print output directory contents
|
136 |
-
# logs = result.stdout
|
137 |
-
# result = print_output_directory(out_dir)
|
138 |
-
|
139 |
-
# return logs+result, str(f"{out_dir}/00000_43_out.mp4")
|
140 |
-
|
141 |
-
# # output 43
|
142 |
-
# # output/ 00000_43_out.mp4
|
143 |
-
# # 00000_43_reference.mp4
|
144 |
-
# # 00000_43_out_reference.mp4
|
145 |
-
|
146 |
-
# # -----------------------------
|
147 |
-
# # Step 3: Create Gradio UI
|
148 |
-
# # -----------------------------
|
149 |
-
# demo = gr.Interface(
|
150 |
-
# fn=inference,
|
151 |
-
# inputs=[
|
152 |
-
# gr.Video(label="Upload Video (MP4)"),
|
153 |
-
# gr.Textbox(label="Caption", placeholder="e.g., Amalfi coast with boats"),
|
154 |
-
# gr.Dropdown(
|
155 |
-
# choices=["zoom_in", "rotate", "orbit", "pan", "loop1"],
|
156 |
-
# label="Camera Motion Type",
|
157 |
-
# value="zoom_in",
|
158 |
-
# ),
|
159 |
-
# ],
|
160 |
-
# outputs=[gr.Textbox(label="Inference Logs"), gr.Video(label="Generated Video")],
|
161 |
-
# title="🎬 EPiC: Efficient Video Camera Control",
|
162 |
-
# description="Upload a video, describe the scene, and apply cinematic camera motion using pretrained EPiC models.",
|
163 |
-
# )
|
164 |
-
|
165 |
-
# # -----------------------------
|
166 |
-
# # Step 4: Launch App
|
167 |
-
# # -----------------------------
|
168 |
-
# if __name__ == "__main__":
|
169 |
-
# demo.launch(server_name="0.0.0.0", server_port=7860)
|
170 |
-
|
171 |
|
172 |
import os
|
173 |
import subprocess
|
174 |
from datetime import datetime
|
175 |
from pathlib import Path
|
176 |
import gradio as gr
|
|
|
177 |
|
178 |
# -----------------------------
|
179 |
# Setup paths and env
|
@@ -206,6 +37,12 @@ download_models()
|
|
206 |
# -----------------------------
|
207 |
# Step 2: Inference Logic
|
208 |
# -----------------------------
|
|
|
|
|
|
|
|
|
|
|
|
|
209 |
def run_epic_inference(video_path, fps, num_frames, target_pose, mode):
|
210 |
temp_input_path = "/app/temp_input.mp4"
|
211 |
output_dir = "/app/output_anchor"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
|
2 |
import os
|
3 |
import subprocess
|
4 |
from datetime import datetime
|
5 |
from pathlib import Path
|
6 |
import gradio as gr
|
7 |
+
import numpy as np
|
8 |
|
9 |
# -----------------------------
|
10 |
# Setup paths and env
|
|
|
37 |
# -----------------------------
|
38 |
# Step 2: Inference Logic
|
39 |
# -----------------------------
|
40 |
+
def estimate_near_far(depths, lower_percentile=5, upper_percentile=95):
|
41 |
+
flat = depths.flatten()
|
42 |
+
near = np.percentile(flat, lower_percentile)
|
43 |
+
far = np.percentile(flat, upper_percentile)
|
44 |
+
return near, far
|
45 |
+
|
46 |
def run_epic_inference(video_path, fps, num_frames, target_pose, mode):
|
47 |
temp_input_path = "/app/temp_input.mp4"
|
48 |
output_dir = "/app/output_anchor"
|
inference/v2v_data/models/infer.py
CHANGED
@@ -49,6 +49,12 @@ class DepthCrafterDemo:
|
|
49 |
print("Xformers is not enabled")
|
50 |
self.pipe.enable_attention_slicing()
|
51 |
|
|
|
|
|
|
|
|
|
|
|
|
|
52 |
def infer(
|
53 |
self,
|
54 |
frames,
|
@@ -87,6 +93,9 @@ class DepthCrafterDemo:
|
|
87 |
depths *= 3900 # compatible with da output
|
88 |
depths[depths < 1e-5] = 1e-5
|
89 |
depths = 10000.0 / depths
|
|
|
|
|
|
|
90 |
depths = depths.clip(near, far)
|
91 |
|
92 |
return depths
|
|
|
49 |
print("Xformers is not enabled")
|
50 |
self.pipe.enable_attention_slicing()
|
51 |
|
52 |
+
def estimate_near_far(self, depths, lower_percentile=5, upper_percentile=95):
|
53 |
+
flat = depths.flatten()
|
54 |
+
near = np.percentile(flat, lower_percentile)
|
55 |
+
far = np.percentile(flat, upper_percentile)
|
56 |
+
return near, far
|
57 |
+
|
58 |
def infer(
|
59 |
self,
|
60 |
frames,
|
|
|
93 |
depths *= 3900 # compatible with da output
|
94 |
depths[depths < 1e-5] = 1e-5
|
95 |
depths = 10000.0 / depths
|
96 |
+
|
97 |
+
near, far = self.estimate_near_far(depths)
|
98 |
+
print(f"Estimated near: {near}, far: {far}")
|
99 |
depths = depths.clip(near, far)
|
100 |
|
101 |
return depths
|