Spaces:
Build error
Build error
File size: 6,494 Bytes
f05bf05 d1f040d f05bf05 d1f040d f05bf05 d1f040d 1f5dc6b d1f040d f05bf05 54cd385 f05bf05 afb6570 f05bf05 d1f040d f05bf05 d1f040d f05bf05 d1f040d f05bf05 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 |
### 1. Imports and class names setup ###
import gradio as gr
import os
import requests
import torch
import numpy as np
from roboflow import Roboflow
import cv2
rf = Roboflow(api_key="PO54lH9XBJxPjmlAvQsW")
project = rf.workspace().project("no_glasses")
model = project.version(1).model
file_urls = [
'https://www.dropbox.com/s/7sjfwncffg8xej2/video_7.mp4?dl=1'
]
def download_file(url, save_name):
url = url
if not os.path.exists(save_name):
file = requests.get(url)
open(save_name, 'wb').write(file.content)
for i, url in enumerate(file_urls):
if 'mp4' in file_urls[i]:
download_file(
file_urls[i],
f"video.mp4"
)
else:
download_file(
file_urls[i],
f"image_{i}.jpg"
)
video_path = [['video.mp4']]
from model import create_effnetb2_model
from timeit import default_timer as timer
from typing import Tuple, Dict
# Setup class names
class_names = ["Yes","No"]
### 2. Model and transforms preparation ###
# Create EffNetB2 model
effnetb2, effnetb2_transforms = create_effnetb2_model(
num_classes=2, # len(class_names) would also work
)
# Load saved weights
effnetb2.load_state_dict(
torch.load(
f="glass_model.pth",
map_location=torch.device("cpu"), # load to CPU
)
)
def detect(imagepath):
pix=model.predict(imagepath, confidence=40, overlap=30)
pix=pix.json()
img=cv2.imread(imagepath)
x1,x2,y1,y2=[],[],[],[]
for i in pix.keys():
if i=="predictions":
for j in pix["predictions"]:
for a,b in j.items():
if a=="x":
x1.append(b)
if a=="y":
y1.append(b)
if a=="width":
x2.append(b)
if a=="height":
y2.append(b)
for p in range(0,len(x1)):
x2[p]=x2[p]+x1[p]
for p in range(0,len(x1)):
y2[p]=y2[p]+x1[p]
for (x11,y11,x12,y12) in zip(x1,y1,x2,y2):
cv2.rectangle(
img,
(x11,y11),
(x12,y12),
color=(0, 0, 255),
thickness=2,
lineType=cv2.LINE_AA
)
return img
#cv2.imshow("kamehamehaa",img)
def show_preds_video(video_path):
cap = cv2.VideoCapture(video_path)
while(cap.isOpened()):
ret, frame = cap.read()
if ret:
frame_copy = frame.copy()
pix=model.predict(frame, confidence=40, overlap=30)
pix=pix.json()
x1,x2,y1,y2=[],[],[],[]
for i in pix.keys():
if i=="predictions":
for j in pix["predictions"]:
for a,b in j.items():
if a=="x":
x1.append(b)
if a=="y":
y1.append(b)
if a=="width":
x2.append(b)
if a=="height":
y2.append(b)
for p in range(0,len(x1)):
x2[p]=x2[p]+x1[p]
for p in range(0,len(x1)):
y2[p]=y2[p]+x1[p]
for (x11,y11,x12,y12) in zip(x1,y1,x2,y2):
cv2.rectangle(
img,
(x11,y11),
(x12,y12),
color=(0, 0, 255),
thickness=2,
lineType=cv2.LINE_AA
)
yield cv2.cvtColor(frame_copy, cv2.COLOR_BGR2RGB)
### 3. Predict function ###
# Create predict function
def predict(img) -> Tuple[Dict, float]:
"""Transforms and performs a prediction on img and returns prediction and time taken.
"""
# Start the timer
start_time = timer()
# Transform the target image and add a batch dimension
img = effnetb2_transforms(img).unsqueeze(0)
# Put model into evaluation mode and turn on inference mode
effnetb2.eval()
with torch.inference_mode():
# Pass the transformed image through the model and turn the prediction logits into prediction probabilities
pred_probs = torch.softmax(effnetb2(img), dim=1)
# Create a prediction label and prediction probability dictionary for each prediction class (this is the required format for Gradio's output parameter)
pred_labels_and_probs = {class_names[i]: float(pred_probs[0][i]) for i in range(len(class_names))}
# Calculate the prediction time
pred_time = round(timer() - start_time, 5)
# Return the prediction dictionary and prediction time
return pred_labels_and_probs, pred_time
### 4. Gradio app ###
# Create title, description and article strings
title = "Safety Glasses Detector"
description = "An EfficientNetB2 feature extractor computer vision model to classify images of Safety glasses at construction sites"
article = "(https://www.learnpytorch.io/)."
# Create examples list from "examples/" directory
#example_list = [["examples/" + example] for example in os.listdir("examples")]
inputs_image = [
gr.components.Image(type="filepath", label="Input Image"),
]
outputs_image = [
gr.components.Image(type="numpy", label="Output Image"),
]
inputs_video = [
gr.components.Video(type="filepath", label="Input Video"),
]
outputs_video = [
gr.components.Image(type="numpy", label="Output Image"),
]
# Create the Gradio demo
app1 = gr.Interface(fn=predict, # mapping function from input to output
inputs=gr.Image(type="pil"), # what are the inputs?
outputs=[gr.Label(num_top_classes=2, label="Predictions"), # what are the outputs?
gr.Number(label="Prediction time (s)")], # our fn has two outputs, therefore we have two outputs
title=title,
description=description,
article=article)
app2=gr.Interface(fn=detect,
inputs=inputs_image,
outputs=outputs_image,
title=title)
app3=gr.Interface(
fn=show_preds_video,
inputs=inputs_video,
outputs=outputs_video,
examples=video_path,
cache_examples=False,
)
demo = gr.TabbedInterface([app1, app2,app3], ["Classify", "Detect","Video Interface"])
# Launch the demo!
demo.launch()
|