luoyetx / joint-face-detection-and-alignment Goto Github PK

Can this framework be used to train human detection models? net‘s’ weight height rate isn't 1:1

貌似提前终止训练的话，显寸不会回收。。。

这边的 idx_pos 改成 idx_part

Hello, thank you for sharing. I want to ask a stupid question, how do you save your log as 1130.log?

Traceback (most recent call last):
File "/usr/lib/python3.5/multiprocessing/queues.py", line 247, in _feed
send_bytes(obj)
File "/usr/lib/python3.5/multiprocessing/connection.py", line 200, in send_bytes
self._send_bytes(m[offset:offset + size])
Traceback (most recent call last):
Traceback (most recent call last):
Traceback (most recent call last):
Traceback (most recent call last):
Traceback (most recent call last):
File "/usr/lib/python3.5/multiprocessing/queues.py", line 247, in _feed
send_bytes(obj)
File "/usr/lib/python3.5/multiprocessing/connection.py", line 200, in send_bytes
self._send_bytes(m[offset:offset + size])
Traceback (most recent call last):
File "/usr/lib/python3.5/multiprocessing/queues.py", line 247, in _feed
send_bytes(obj)
Traceback (most recent call last):
File "/usr/lib/python3.5/multiprocessing/connection.py", line 404, in _send_bytes
self._send(header + buf)
File "/usr/lib/python3.5/multiprocessing/connection.py", line 404, in _send_bytes
self._send(header + buf)
File "/usr/lib/python3.5/multiprocessing/queues.py", line 247, in _feed
send_bytes(obj)
File "/usr/lib/python3.5/multiprocessing/queues.py", line 247, in _feed
send_bytes(obj)
File "/usr/lib/python3.5/multiprocessing/connection.py", line 368, in _send
n = write(self._handle, buf)
File "/usr/lib/python3.5/multiprocessing/connection.py", line 368, in _send
n = write(self._handle, buf)
BrokenPipeError: [Errno 32] Broken pipe
File "/usr/lib/python3.5/multiprocessing/queues.py", line 247, in _feed
send_bytes(obj)
File "/usr/lib/python3.5/multiprocessing/connection.py", line 200, in send_bytes
self._send_bytes(m[offset:offset + size])
File "/usr/lib/python3.5/multiprocessing/connection.py", line 200, in send_bytes
self._send_bytes(m[offset:offset + size])
File "/usr/lib/python3.5/multiprocessing/connection.py", line 200, in send_bytes
self._send_bytes(m[offset:offset + size])
File "/usr/lib/python3.5/multiprocessing/connection.py", line 200, in send_bytes
self._send_bytes(m[offset:offset + size])
File "/usr/lib/python3.5/multiprocessing/connection.py", line 404, in _send_bytes
self._send(header + buf)
File "/usr/lib/python3.5/multiprocessing/connection.py", line 404, in _send_bytes
self._send(header + buf)
File "/usr/lib/python3.5/multiprocessing/connection.py", line 368, in _send
n = write(self._handle, buf)
Fatal Python error: could not acquire lock for <_io.BufferedWriter name=''> at interpreter shutdown, possibly due to daemon threads

Thread 0x00007fa9a22b9700 (most recent call first):
File "/usr/lib/python3.5/traceback.py", line 101 in print_exception
File "/usr/lib/python3.5/traceback.py", line 159 in print_exc
File "/usr/lib/python3.5/multiprocessing/queues.py", line 264 in _feed
File "/usr/lib/python3.5/threading.py", line 862 in run
File "/usr/lib/python3.5/threading.py", line 914 in _bootstrap_inner
File "/usr/lib/python3.5/threading.py", line 882 in _bootstrap

Thread 0x00007fa9d6647700 (most recent call first):
File "/usr/lib/python3.5/traceback.py", line 101 in print_exception
File "/usr/lib/python3.5/traceback.py", line 159 in print_exc
File "/usr/lib/python3.5/multiprocessing/queues.py", line 264 in _feed
File "/usr/lib/python3.5/threading.py", line 862 in run
File "/usr/lib/python3.5/threading.py", line 914 in _bootstrap_inner
File "/usr/lib/python3.5/threading.py", line 882 in _bootstrap

Thread 0x00007fa9d8e48700 (most recent call first):
File "/usr/lib/python3.5/traceback.py", line 101 in print_exception
File "/usr/lib/python3.5/traceback.py", line 159 in print_exc
File "/usr/lib/python3.5/multiprocessing/queues.py", line 264 in _feed
File "/usr/lib/python3.5/threading.py", line 862 in run
File "/usr/lib/python3.5/threading.py", line 914 in _bootstrap_inner
File "/usr/lib/python3.5/threading.py", line 882 in _bootstrap

Thread 0x00007fa9d9649700 (most recent call first):
File "/usr/lib/python3.5/traceback.py", line 101 in print_exception
File "/usr/lib/python3.5/traceback.py", line 159 in print_exc
File "/usr/lib/python3.5/multiprocessing/queues.py", line 264 in _feed
File "/usr/lib/python3.5/threading.py", line 862 in run
File "/usr/lib/python3.5/threading.py", line 914 in _bootstrap_inner
File "/usr/lib/python3.5/threading.py", line 882 in _bootstrap

Thread 0x00007fa9927fc700 (most recent call first):
File "/usr/lib/python3.5/traceback.py", line 101 in print_exception
File "/usr/lib/python3.5/traceback.py", line 159 in print_exc
File "/usr/lib/python3.5/multiprocessing/queues.py", line 264 in _feed
File "/usr/lib/python3.5/threading.py", line 862 in run
File "/usr/lib/python3.5/threading.py", line 914 in _bootstrap_inner
File "/usr/lib/python3.5/threading.py", line 882 in _bootstrap

Thread 0x00007fa9a0ab6700 (most recent call first):
File "/usr/lib/python3.5/traceback.py", line 101 in print_exception
File "/usr/lib/python3.5/traceback.py", line 159 in print_exc
File "/usr/lib/python3.5/multiprocessing/queues.py", line 264 in _feed
File "/usr/lib/python3.5/threading.py", line 862 in run
File "/usr/lib/python3.5/threading.py", line 914 in _bootstrap_inner
File "/usr/lib/python3.5/threading.py", line 882 in _bootstrap

Thread 0x00007fa993fff700 (most recent call first):
File "/usr/lib/python3.5/traceback.py", line 101 in print_exception
File "/usr/lib/python3.5/traceback.py", line 159 in print_exc
File "/usr/lib/python3.5/multiprocessing/queues.py", line 264 in _feed
File "/usr/lib/python3.5/threading.py", line 862 in run
File "/usr/lib/python3.5/threading.py", line 914 in _bootstrap_inner
File "/usr/lib/python3.5/threading.py", line 882 in _bootstrap

Current thread 0x00007fa9e6ee9700 (most recent call first):
Aborted (core dumped)

Traceback (most recent call last):
File "jfda/prepare.py", line 544, in
gen_wider()
File "jfda/prepare.py", line 269, in gen_wider
train_data, val_data = load_wider()
File "/home/haneesh/Desktop/mtcnn-head-detection-master/jfda/utils.py", line 172, in load_wider
train_data = gen(os.path.join(txt_dir, 'wider_face_train_bbx_gt.txt'), train_mapper)
File "/home/haneesh/Desktop/mtcnn-head-detection-master/jfda/utils.py", line 144, in gen
x, y, w, h = [float(_) for _ in components]
ValueError: too many values to unpack (expected 4)

thank you

你好，非常感谢你的开源，这是我目前能跑完整的唯一一个mtcnn....
可能是我比较菜，但是我看了你的网络结构和lossfunction应该是我看到的所有mtcnn里面最清晰明了的了
我在训练R层的时候，发现pos_acc有较强的波动性不知道是什么原因，如下训练部分打印
I0602 11:04:08.421706 55441 solver.cpp:239] Iteration 13500 (39.3993 iter/s, 12.6906s/500 iters), loss = 1.55104
I0602 11:04:08.421797 55441 solver.cpp:258] Train net output #0: face_cls_loss = 0.0894116 (* 1 = 0.0894116 loss)
I0602 11:04:08.421815 55441 solver.cpp:258] Train net output #1: face_cls_neg_acc = 0.994792 (* 0.5 = 0.497396 loss)
I0602 11:04:08.421825 55441 solver.cpp:258] Train net output #2: face_cls_pos_acc = 0.953125 (* 1 = 0.953125 loss)
I0602 11:04:08.421844 55441 sgd_solver.cpp:112] Iteration 13500, lr = 0.005
I0602 11:04:21.311125 55441 solver.cpp:239] Iteration 14000 (38.7931 iter/s, 12.8889s/500 iters), loss = 1.55069
I0602 11:04:21.311210 55441 solver.cpp:258] Train net output #0: face_cls_loss = 0.153639 (* 1 = 0.153639 loss)
I0602 11:04:21.311228 55441 solver.cpp:258] Train net output #1: face_cls_neg_acc = 0.981771 (* 0.5 = 0.490885 loss)
I0602 11:04:21.311240 55441 solver.cpp:258] Train net output #2: face_cls_pos_acc = 0.882812 (* 1 = 0.882812 loss)

I can not see any explanation about Face Alignment. It this project can align the faces? Could you provide some details please?

Hi luoyetx:
thank you for your wonderful work and open source!
def set_batch_num(self, n1, n2, n3, n4):
'''set data type number
# n1 for negatives, n2 for positives, n3 for part faces, n4 for landmark faces
net_input_size for network input size (width, height)

def set_data_queue(self, queue):
'''the queue should put a minibatch with size of (positives, negatives, part faces, landmark faces) =
(n1, n2, n3, n4) in a dict
'''
so which one is correct, look through the code, negative is n1,and positive is n2, is it right?
Forest

您好，我把您的 “layers”文件夹的层复制到我的caffe里面编译的时候，会报错：
error: ‘class caffe::LayerParameter’ has no member named ‘jfda_loss_param’
请问您知道该怎么解决吗？谢谢！

minibatch.py的_make_transform成员在做flip时，bbox坐标的变换是否有问题，应该为bbox[0], bbox[2] =1 -bbox[2], 1-bbox[0]

Please explain a bit about the Neural Network that you used in this project.

How many hidden layers does it have? Have you performed data augmentation, batch normalization, ensembling or dropout? Could you explain them?

when i run command prepare.py --net p --wider --celeba --worker 8
its happend:

File "F:/myself/mtcnn/caffe/Joint-Face-Detection-and-Alignment-master/jfda/prepare.py", line 518, in verify
for i, (data, bbox_target) in enumerate(positives):
ValueError: too many values to unpack (expected 2)

need help thank you

您好 很棒的repo 謝謝開源
關於總結有一些問題
JFDA在檢測時應該是沒有用到滑動窗口的，只建了金字塔後將圖像全部resize丟入網路