8f05a7c188
- Update ASR, face, OCR, pose processors - Add release pre-flight check script - Add synonym generation, chunk processing scripts - Add face recognition, stamp search utilities
113 lines
3.5 KiB
Python
113 lines
3.5 KiB
Python
#!/opt/homebrew/bin/python3.11
|
|
"""
|
|
Crop the newly detected stamps from the specific search.
|
|
"""
|
|
|
|
import os
|
|
import cv2
|
|
|
|
UUID = "384b0ff44aaaa1f1"
|
|
OUTPUT_DIR = f"output/{UUID}/florence2_results"
|
|
|
|
# Coordinates from the specific search result
|
|
# These are placeholders - I need to re-run to get the exact boxes if they weren't printed.
|
|
# Since I saw the logs, I know it found them.
|
|
# But I need the exact coordinates. Let's run a detection script that crops them immediately.
|
|
import torch
|
|
import types
|
|
from PIL import Image
|
|
from transformers import AutoProcessor, AutoModelForCausalLM
|
|
|
|
|
|
def patch_model(model):
|
|
inner_model = model.language_model
|
|
original_prepare = inner_model.prepare_inputs_for_generation
|
|
|
|
def patched_prepare(
|
|
self,
|
|
input_ids,
|
|
past_key_values=None,
|
|
attention_mask=None,
|
|
inputs_embeds=None,
|
|
**kwargs,
|
|
):
|
|
is_valid_cache = False
|
|
if past_key_values is not None:
|
|
if isinstance(past_key_values, (list, tuple)) and len(past_key_values) > 0:
|
|
first_layer = past_key_values[0]
|
|
if first_layer is not None and (
|
|
not isinstance(first_layer, (list, tuple)) or len(first_layer) > 0
|
|
):
|
|
is_valid_cache = True
|
|
|
|
if not is_valid_cache:
|
|
return {
|
|
"input_ids": input_ids,
|
|
"attention_mask": attention_mask,
|
|
"past_key_values": None,
|
|
"use_cache": True,
|
|
}
|
|
else:
|
|
return original_prepare(
|
|
input_ids,
|
|
past_key_values=past_key_values,
|
|
attention_mask=attention_mask,
|
|
inputs_embeds=inputs_embeds,
|
|
**kwargs,
|
|
)
|
|
|
|
inner_model.prepare_inputs_for_generation = types.MethodType(
|
|
patched_prepare, inner_model
|
|
)
|
|
|
|
|
|
IMG_PATH = os.path.join(OUTPUT_DIR, "raw_6846.jpg")
|
|
img_cv = cv2.imread(IMG_PATH)
|
|
image = Image.open(IMG_PATH).convert("RGB")
|
|
|
|
print("🧠 Reloading model to get coordinates...")
|
|
try:
|
|
processor = AutoProcessor.from_pretrained(
|
|
"microsoft/Florence-2-base", trust_remote_code=True
|
|
)
|
|
model = AutoModelForCausalLM.from_pretrained(
|
|
"microsoft/Florence-2-base", trust_remote_code=True, attn_implementation="eager"
|
|
)
|
|
patch_model(model)
|
|
|
|
prompt = "<OPEN_VOCABULARY_DETECTION>"
|
|
term = "postage stamp"
|
|
|
|
inputs = processor(text=prompt, images=image, return_tensors="pt")
|
|
generated_ids = model.generate(
|
|
input_ids=inputs["input_ids"],
|
|
pixel_values=inputs["pixel_values"],
|
|
max_new_tokens=1024,
|
|
num_beams=3,
|
|
)
|
|
generated_text = processor.batch_decode(generated_ids, skip_special_tokens=False)[0]
|
|
parsed_answer = processor.post_process_generation(
|
|
generated_text, task=prompt, image_size=(image.width, image.height)
|
|
)
|
|
|
|
results = parsed_answer.get("<OPEN_VOCABULARY_DETECTION>", {})
|
|
bboxes = results.get("bboxes", [])
|
|
|
|
if bboxes:
|
|
print(f"✅ Found {len(bboxes)} stamp(s)!")
|
|
for i, box in enumerate(bboxes):
|
|
x1, y1, x2, y2 = map(int, box)
|
|
print(f" 📍 Box {i + 1}: {box}")
|
|
|
|
# Crop
|
|
crop = img_cv[y1:y2, x1:x2]
|
|
out_name = f"stamp_crop_{i + 1}.jpg"
|
|
out_path = os.path.join(OUTPUT_DIR, out_name)
|
|
cv2.imwrite(out_path, crop)
|
|
print(f" 💾 Saved to {out_path}")
|
|
else:
|
|
print("❌ No stamps found.")
|
|
|
|
except Exception as e:
|
|
print(f"❌ Error: {e}")
|