def test():
img_arr = read_image('demo.jpg')
img = t.from_numpy(img_arr)[None]
faster_rcnn = FasterRCNN()
trainer = FasterRCNNTrainer(faster_rcnn).cuda()
trainer.load('weights/chainer_best_model_converted_to_pytorch_0.7053.pth')
opt.caffe_pretrain = True
_bboxes, _labels, _scores = trainer.faster_rcnn.predict(img, visualize=True)
vis_bbox(at.tonumpy(img[0]),
at.tonumpy(_bboxes[0]),
at.tonumpy(_labels[0]).reshape(-1),
at.tonumpy(_scores[0]).reshape(-1))
def predict(self, imgs=[]):
imglist = []
for i in imgs:
img_path = os.path.join(self.imgs_path, i)
img = read_image(img_path)
if self.isneed_enhance:
img = Image_Enhance().api(img)
img = t.from_numpy(img)[None]
imglist.append(img)
for index, img in enumerate(imglist):
starttime = datetime.datetime.now()
_bboxes, _labels, _scores = self.trainer.faster_rcnn.predict(
img, visualize=True)
endtime = datetime.datetime.now()
print('predict time consum=%s' % round(
(endtime-starttime).microseconds/1000000+(endtime-starttime).seconds, 6))
if self.imgs_vis_path:
img_path = os.path.join(self.imgs_vis_path, imgs[index])
img = read_image(img_path)
img = t.from_numpy(img)[None]
ax = vis_bbox(at.tonumpy(img[0]),
at.tonumpy(_bboxes[0]),
at.tonumpy(_labels[0]).reshape(-1),
at.tonumpy(_scores[0]).reshape(-1))
fig = ax.get_figure()
fig.savefig("output.png")
def single_predict(self, img_path=''):
starttime = datetime.datetime.now()
img = read_image(img_path)
img = t.from_numpy(img)[None]
_bboxes, _labels, _scores = self.trainer.faster_rcnn.predict(
img, visualize=True)
endtime = datetime.datetime.now()
print('predict time consum=%s' % round(
(endtime-starttime).microseconds/1000000+(endtime-starttime).seconds, 6))
ax = vis_bbox(at.tonumpy(img[0]),
at.tonumpy(_bboxes[0]),
at.tonumpy(_labels[0]).reshape(-1),
at.tonumpy(_scores[0]).reshape(-1))
fig = ax.get_figure()
fig.savefig("output.png")
import os
import torch as t
from utils.config import opt
from model import FasterRCNNVGG16
from trainer import FasterRCNNTrainer
from data.util import read_image
from utils.vis_tool import vis_bbox
from utils import array_tool as at
img = read_image('misc/demo.jpg')
img = t.from_numpy(img)[None]
faster_rcnn = FasterRCNNVGG16()
trainer = FasterRCNNTrainer(faster_rcnn).cuda()
trainer.load('./fasterrcnn_12222105_0.712649824453_caffe_pretrain.pth')
opt.caffe_pretrain = False # this model was trained from torchvision-pretrained model
_bboxes, _labels, _scores = trainer.faster_rcnn.predict(img, visualize=True)
vis_bbox(at.tonumpy(img[0]), at.tonumpy(_bboxes[0]),
at.tonumpy(_labels[0]).reshape(-1),
at.tonumpy(_scores[0]).reshape(-1))
# This can be removed once PyTorch 0.4.x is out.
# See https://discuss.pytorch.org/t/question-about-rebuild-tensor-v2/14560
import torch._utils
try:
torch._utils._rebuild_tensor_v2
except AttributeError:
def _rebuild_tensor_v2(storage, storage_offset, size, stride, requires_grad, backward_hooks):
tensor = torch._utils._rebuild_tensor(storage, storage_offset, size, stride)
tensor.requires_grad = requires_grad
tensor._backward_hooks = backward_hooks
return tensor
torch._utils._rebuild_tensor_v2 = _rebuild_tensor_v2
#%%
faster_rcnn = FasterRCNNVGG16()
trainer = FasterRCNNTrainer(faster_rcnn).cuda()
trainer.load('./checkpoints/fasterrcnn_09031352_0')
opt.caffe_pretrain=True # this model was trained from caffe-pretrained model
# Plot examples on training set
dataset = RSNADataset(opt.root_dir)
for i in range(0, len(dataset)):
sample = dataset[i]
img = sample['image']
ori_img_ = inverse_normalize(at.tonumpy(img))
# plot predicti bboxes
_bboxes, _labels, _scores = trainer.faster_rcnn.predict([ori_img_], visualize=True)
pred_img = vis_bbox(ori_img_,
at.tonumpy(_bboxes[0]),
at.tonumpy(_labels[0]).reshape(-1),
at.tonumpy(_scores[0]))
from utils.vis_tool import vis_bbox
from utils import array_tool as at
from utils.average import AverageVal
import numpy as np
import matplotlib.pyplot as plt
os.environ["CUDA_VISIBLE_DEVICES"] = "4"
logger = AverageVal()
faster_rcnn = FasterRCNNVGG16()
trainer = FasterRCNNTrainer(faster_rcnn, logger).cuda()
trainer.load("checkpoints/fasterrcnn_03090654_0.6984418117245029")
for i in range(1, 192):
img_path = "movie/input/{}.jpg".format(i)
img = read_image(img_path)
img = t.from_numpy(img)[None]
opt.caffe_pretrain = False # this model was trained from caffe-pretrained model
_bboxes, _labels, _scores = trainer.faster_rcnn.predict(img, visualize=True)
output_path = "movie/output/{}.jpg".format(i)
vis_bbox(
at.tonumpy(img[0]),
at.tonumpy(_bboxes[0]),
at.tonumpy(_labels[0]).reshape(-1),
at.tonumpy(_scores[0]).reshape(-1),
figsize=(15, 8.5),
)
plt.axis("off")
plt.savefig(output_path)
import os
import torch as t
from utils.config import Config
from model import FasterRCNNVGG16
from trainer import FasterRCNNTrainer
from data.util import read_image
from utils.vis_tool import vis_bbox
from utils import array_tool as at
%matplotlib inline
img_name = 'demo.jpg'
raw_img = read_image(f'/content/drive/My Drive/lq_det_hyper/lq_det/misc/{img_name}')
raw_img = t.from_numpy(raw_img).unsqueeze(dim=0)
faster_rcnn = FasterRCNNVGG16()
trainer = FasterRCNNTrainer(faster_rcnn, using_visdom=False).cuda()
trainer.load('/content/drive/My Drive/lq_det_hyper/lq_det/ckpt/fasterrcnn_12222105_0.712649824453_caffe_pretrain.pth')
Config.caffe_vgg=True # this model was trained from caffe-pretrained model
_bboxes, _labels, _scores = trainer.faster_rcnn.predict(raw_img, visualize=True)
img, bbox, label, score = (at.tonumpy(raw_img[0]), at.tonumpy(_bboxes[0]), at.tonumpy(_labels[0]).reshape(-1), at.tonumpy(_scores[0]).reshape(-1))
vis_bbox(img, bbox, label, score)
import matplotlib.pyplot as plt
plt.show()