Duplicate from khaclinh/self-driving-anonymization

Co-authored-by: Linh Trinh <[email protected]>

.gitattributes

@@ -0,0 +1,31 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,14 @@
+---
+title: Self Driving Anonymization
+emoji: 📈
+colorFrom: yellow
+colorTo: gray
+sdk: gradio
+sdk_version: 3.4.1
+app_file: app.py
+pinned: false
+license: cc-by-nc-4.0
+duplicated_from: khaclinh/self-driving-anonymization
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,133 @@
+# Author: khaclinh
+import os
+
+os.system('pip install yolox')
+
+import gradio as gr
+import torch
+import numpy as np
+from PIL import Image
+import importlib
+
+import cv2 
+
+from yolox.utils import postprocess
+from yolox.data.data_augment import ValTransform
+
+ckpt_file = 'model_weights/best_ckpt.pth'
+
+# get YOLOX experiment
+current_exp = importlib.import_module('pp4av_exp')
+exp = current_exp.Exp()
+
+# set inference parameters
+test_size = (800, 800)
+num_classes = 2
+nmsthre = 0.3
+
+GDPR_CLASSES = (
+    "Face",
+    "Plate"
+)
+
+
+# get YOLOX model
+model = exp.get_model()
+#model.cuda()
+model.eval()
+
+# get custom trained checkpoint
+ckpt = torch.load(ckpt_file, map_location="cpu")
+model.load_state_dict(ckpt["model"])
+
+
+def yolox_inference(img, model, prob_threshold, test_size): 
+    bboxes = []
+    bbclasses = []
+    scores = []
+    
+    preproc = ValTransform(legacy = False)
+
+    tensor_img, _ = preproc(img, None, test_size)
+    tensor_img = torch.from_numpy(tensor_img).unsqueeze(0)
+    tensor_img = tensor_img.float()
+    #tensor_img = tensor_img.cuda()
+
+    with torch.no_grad():
+        outputs = model(tensor_img)
+        outputs = postprocess(
+                    outputs, num_classes, prob_threshold,
+                    nmsthre, class_agnostic=True
+                )
+
+    if outputs[0] is None:
+        return [], [], []
+    
+    outputs = outputs[0].cpu()
+    bboxes = outputs[:, 0:4]
+
+    bboxes /= min(test_size[0] / img.shape[0], test_size[1] / img.shape[1])
+    bbclasses = outputs[:, 6]
+    scores = outputs[:, 4] * outputs[:, 5]
+    
+    return bboxes, bbclasses, scores
+
+
+def draw_yolox_predictions(img, bboxes, scores, bbclasses, prob_threshold, classes_dict):
+    for i in range(len(bboxes)):
+            box = bboxes[i]
+            cls_id = int(bbclasses[i])
+            score = scores[i]
+            if score < prob_threshold:
+                continue
+            x0 = int(box[0])
+            y0 = int(box[1])
+            x1 = int(box[2])
+            y1 = int(box[3])
+            if cls_id == 0:
+
+                cv2.rectangle(img, (x0, y0), (x1, y1), (0, 255, 0), 2)
+                cv2.putText(img, '{}:{:.1f}%'.format(classes_dict[cls_id], score * 100), (x0, y0 - 3), cv2.FONT_HERSHEY_PLAIN, 0.8, (0,255,0), thickness = 1)
+            else:
+                cv2.rectangle(img, (x0, y0), (x1, y1), (255, 0, 0), 2)
+                cv2.putText(img, '{}:{:.1f}%'.format(classes_dict[cls_id], score * 100), (x0, y0 - 3), cv2.FONT_HERSHEY_PLAIN, 0.8, (255,0,0), thickness = 1)
+            
+            
+    return img
+
+
+def pp4av_detect(img, prob_threshold=0.1):
+    # Convert PIL image to CV2
+    open_cv_image = np.array(img) 
+    # Convert RGB to BGR 
+    open_cv_image = open_cv_image[:, :, ::-1].copy() 
+
+    bboxes, bbclasses, scores = yolox_inference(open_cv_image, model, prob_threshold, test_size)
+
+    out = cv2.cvtColor(open_cv_image, cv2.COLOR_BGR2RGB)
+    # Draw predictions
+    out_image = draw_yolox_predictions(out, bboxes, scores, bbclasses, prob_threshold, GDPR_CLASSES)
+    
+    return Image.fromarray(out_image)
+
+
+img_input = gr.inputs.Image(type='pil', label="Original Image")
+img_output = gr.outputs.Image(type="pil", label="Output Image")
+
+prob_threshold_slider = gr.Slider(minimum=0, maximum=1.0, step=0.01, value=0.1, label="Confidence Threshold")
+
+title = "PP4AV: Deep Learning model for Data Anonymization in Autonomous Driving"
+description = "Detecting faces and license plates in image data from self-driving cars. Take a picture, upload an image, or click an example image to use."
+article = ""
+
+examples = [['data/fisheye.jpg'], ['data/zurich.jpg'], ['data/stuttgart.jpg'], ['data/strasbourg.jpg']]
+gr.Interface(
+    fn = pp4av_detect, 
+    inputs = [img_input, prob_threshold_slider], 
+    outputs = img_output, 
+    title = title, 
+    description = description, 
+    article = article, 
+    examples = examples, 
+    theme = "huggingface"
+).launch(enable_queue=True)

model_weights/.keep

@@ -0,0 +1 @@
+

model_weights/best_ckpt.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f2abeffba9454f8c88a1cb42dd1358ce054f5a4656bed4c9f1542911f5e5f99
+size 433859563

pp4av_exp.py

@@ -0,0 +1,48 @@
+#!/usr/bin/env python3
+# -*- coding:utf-8 -*-
+# Copyright (c) Megvii, Inc. and its affiliates.
+
+import os
+
+from yolox.exp import Exp as MyExp
+
+class Exp(MyExp):
+    def __init__(self):
+        super(Exp, self).__init__()
+        self.depth = 1.0 # indicate size yolo model
+        self.width = 1.0 #
+        self.exp_name = os.path.split(os.path.realpath(__file__))[1].split(".")[0]
+
+        self.data_dir = ''
+        self.train_ann = ''
+        self.val_ann = '' 
+        self.test_ann = ''
+        
+        self.num_classes = 2
+        self.data_num_workers = 32 # number of cpu for splitting batch
+   
+        self.input_size = (800, 800)   
+        self.print_interval = 100
+        self.eval_interval = 1
+        self.test_size = (800, 800)
+        self.enable_mixup = True
+        self.mosaic_scale = (0.5, 1.5)
+        self.max_epoch = 300 
+        self.hsv_prob = 1.0
+
+        self.degrees = 20.0
+        self.translate = 0.2
+        self.shear = 2.0
+        # Turn off mosaic
+        self.mosaic_prob = 1.0
+        # Turn off Mixup
+        self.mixup_prob = 1.0
+        # Change SGD by ADAM
+        
+
+        self.basic_lr_per_img = 0.01 / 28.0
+        self.no_aug_epochs = 15
+        self.min_lr_ratio = 0.05
+        self.ema = True
+
+        self.nmsthre = 0.3

requirements.txt

@@ -0,0 +1,9 @@
+gradio
+torch
+torchvision
+numpy
+opencv-python
+seaborn
+tabulate
+loguru
+thop