def evaluate(args, model, image_list, seg_classes, device):
im_size = tuple(args.im_size)
# get color map for pascal dataset
if args.dataset == 'pascal':
from utilities.color_map import VOCColormap
cmap = VOCColormap().get_color_map_voc()
else:
cmap = None
model.eval()
inter_meter = AverageMeter()
union_meter = AverageMeter()
miou_class = MIOU(num_classes=seg_classes)
for i, imgName in tqdm(enumerate(image_list)):
img = Image.open(imgName).convert('RGB')
w, h = img.size
img = data_transform(img, im_size)
img = img.unsqueeze(0) # add a batch dimension
img = img.to(device)
img_out = model(img)
img_out = img_out.squeeze(0) # remove the batch dimension
img_out = img_out.max(0)[1].byte() # get the label map
img_out = img_out.to(device='cpu').numpy()
if args.dataset == 'city':
# cityscape uses different IDs for training and testing
# so, change from Train IDs to actual IDs
img_out = relabel(img_out)
img_out = Image.fromarray(img_out)
# resize to original size
img_out = img_out.resize((w, h), Image.NEAREST)
# pascal dataset accepts colored segmentations
if args.dataset == 'pascal':
img_out.putpalette(cmap)
# save the segmentation mask
name = imgName.split('/')[-1]
img_extn = imgName.split('.')[-1]
name = '{}/{}'.format(args.savedir, name.replace(img_extn, 'png'))
img_out.save(name)
import torch
from utilities.print_utils import *
import os
from PIL import Image
from utilities.color_map import VOCColormap
import glob
from torchvision.transforms import functional as F
from transforms.classification.data_transforms import MEAN, STD
from tqdm import tqdm
from argparse import ArgumentParser
COLOR_MAP = VOCColormap().get_color_map()
IMAGE_EXTENSIONS = ['.jpg', '.png', '.jpeg']
def data_transform(img, im_size):
img = img.resize(im_size, Image.BILINEAR)
img = F.to_tensor(img) # convert to tensor (values between 0 and 1)
img = F.normalize(img, MEAN, STD) # normalize the tensor
return img
def run_segmentation(args, model, image_list, device):
im_size = tuple(args.im_size)
model.eval()
with torch.no_grad():
for imgName in tqdm(image_list):
img = Image.open(imgName).convert('RGB')
img_clone = img.copy()
w, h = img.size
img = data_transform(img, im_size)
import argparse
import numpy as np
import torch
import torchvision
from utilities.print_utils import *
from model.detection.ssd import ssd
import os
from model.detection.box_predictor import BoxPredictor
from PIL import Image
import cv2
from utilities.color_map import VOCColormap
import glob
COLOR_MAP = []
for cmap in VOCColormap().get_color_map():
r, g, b = cmap
COLOR_MAP.append((int(r), int(g), int(b)))
FONT_SIZE = cv2.FONT_HERSHEY_SIMPLEX
LABEL_COLOR = [255, 255, 255]
TEXT_THICKNESS = 2
RECT_BORDER_THICKNESS=3
def main(args):
if args.im_size in [300, 512]:
from model.detection.ssd_config import get_config
cfg = get_config(args.im_size)
else:
print_error_message('{} image size not supported'.format(args.im_size))