Update\

.gitignore

@@ -0,0 +1 @@
+**/.DS_Store

Content/README.roboflow.txt

@@ -0,0 +1,17 @@
+
+Anti-Social Classification - v1 Training Data
+==============================
+
+This dataset was exported via roboflow.ai on May 29, 2022 at 11:41 PM GMT
+
+It includes 232 images.
+Anti-Social-Imagery are annotated in YOLO v5 PyTorch format.
+
+The following pre-processing was applied to each image:
+* Auto-orientation of pixel data (with EXIF-orientation stripping)
+* Resize to 416x416 (Stretch)
+
+The following augmentation was applied to create 3 versions of each source image:
+* 50% probability of horizontal flip
+
+

Content/best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebe736fb49492830593165d94e2543de337d82d7acc592e25f8e1a7b33d846f1
+size 14358133

Content/configurations.md

@@ -0,0 +1,7 @@
+model.conf = 0.25  # NMS confidence threshold
+      iou = 0.45  # NMS IoU threshold
+      agnostic = False  # NMS class-agnostic
+      multi_label = False  # NMS multiple labels per box
+      classes = None  # (optional list) filter by class, i.e. = [0, 15, 16] for COCO persons, cats and dogs
+      max_det = 1000  # maximum number of detections per image
+      amp = False  # Automatic Mixed Precision (AMP) inference

Content/data.yaml

@@ -0,0 +1,10 @@
+names:
+- Confederate Flag
+- Gun
+- KKK Triangle
+- KKK
+- Noose
+- Swastika
+nc: 6
+train: /content/datasets/Anti-Social-Classification-1/train/images
+val: /content/datasets/Anti-Social-Classification-1/valid/images

app.py

@@ -0,0 +1,40 @@
+import gradio as gr
+import os
+import torch
+from PIL import Image
+
+                           
+#subprocess.run(["mv","content/custom_data.yaml","./yolov5/data"])         
+
+
+def load_model():
+ '''
+ Loading hub model & setting the preferences for the model  
+ '''
+ model = torch.hub.load('ultralytics/yolov5', 'custom', path='Content/best.pt')
+ model.conf = 0.38 
+ model.dnn=True
+ model.agnostic=True
+ return model
+
+model=load_model()
+#, force_reload=True
+def detect(inp):
+ #g = (size / max(inp.size))  #gain
+ #im = im.resize((int(x * g) for x in im.size), Image.ANTIALIAS)  # resize 
+ results = model(inp,size=640)  # inference
+ results.render()  # updates results.imgs with boxes and labels
+ return Image.fromarray(results.imgs[0])
+ 
+
+inp = gr.inputs.Image(type="pil", label="Original Image")
+output = gr.outputs.Image(type="pil", label="Output Image")
+
+
+io=gr.Interface(fn=detect, inputs=inp, outputs=output, title='CV Social Classification',theme='peach')
+io.launch(debug=True,share=False)
+  
+#examples=['Content/4.jpg','Content/10.jpg','Content/18.jpg']
+
+                                             
+                                                                                                                                       

packages.txt

@@ -0,0 +1 @@
+libgl1-mesa-glx

requirements.txt

@@ -0,0 +1,20 @@
+gradio
+
+# Base ----------------------------------------
+matplotlib>=3.2.2
+numpy>=1.18.5
+opencv-python>=4.1.2
+Pillow>=7.1.2
+PyYAML>=5.3.1
+requests>=2.23.0
+scipy>=1.4.1
+torch>=1.7.0
+torchvision>=0.8.1
+tqdm>=4.41.0
+
+
+
+# Plotting ------------------------------------
+pandas>=1.1.4
+seaborn>=0.11.0
+