wuzheng-sjtu / fastfpn Goto Github PK
View Code? Open in Web Editor NEWTensorflow implementation for "Feature Pyramid Networks for Object Detection"
License: Apache License 2.0
Tensorflow implementation for "Feature Pyramid Networks for Object Detection"
License: Apache License 2.0
It seems there is not a test or evaluate program in this repository, so do you have a plan to add one?
Thank you.
When I run resnet50_test,i meet a problem.
The code in this:
for step in range(FLAGS.max_iters):
start_time = time.time()
_, tot_loss, reg_lossnp, img_id_str, \
rpn_box_loss, rpn_cls_loss, refined_box_loss, refined_cls_loss, mask_loss, \
gt_boxesnp, \
rpn_batch_pos, rpn_batch, refine_batch_pos, refine_batch, mask_batch_pos, mask_batch = \
sess.run([update_op, total_loss, reg_loss, img_id] +
losses +
[gt_boxes] +
batch_info)
The wrong message:
Traceback (most recent call last):
File "/home/zzz/pycharm-community-2017.2.3/helpers/pydev/pydevd.py", line 1599, in
globals = debugger.run(setup['file'], None, None, is_module)
File "/home/zzz/pycharm-community-2017.2.3/helpers/pydev/pydevd.py", line 1026, in run
pydev_imports.execfile(file, globals, locals) # execute the script
File "/home/zzz/FastFPN/unit_test/resnet50_test.py", line 150, in
batch_info)
ValueError: need more than 13 values to unpack
I worked two weeks in this project,i'm very depress.I hope you can give me some suggestion. @DandyWuGit @wuzheng-sjtu
I encounter a problem when I try to run the train.py like this
Traceback (most recent call last):
File "C:/Users/Administrator/Desktop/FastFPN-master/FastFPN-master/train/train.py", line 22, in
import libs.nets.pyramid_network as pyramid_network
File "C:/Users/Administrator/Desktop/FastFPN-master/FastFPN-master/train..\libs\nets\pyramid_network.py", line 9, in
from libs.boxes.roi import roi_cropping
File "C:/Users/Administrator/Desktop/FastFPN-master/FastFPN-master/train..\libs\boxes_init_.py", line 7, in
from . import cython_nms
File "C:/Users/Administrator/Desktop/FastFPN-master/FastFPN-master/train..\libs\boxes\cython_nms.py", line 14, in
bootstrap()
File "C:/Users/Administrator/Desktop/FastFPN-master/FastFPN-master/train..\libs\boxes\cython_nms.py", line 12, in bootstrap
imp.load_dynamic(name, file)
File "D:\Anaconda\envs\tensorflow\lib\imp.py", line 343, in load_dynamic
return _load(spec)
ImportError: DLL load failed: The specified module could not be found.
I think it might have something to do with the version problem, I will be appreciate if you could offer me some advices. THANK YOU.
a great work.
After modified according to my own dataset, it raised the following error:
Caused by op u'pyramid_2/ROIEncoder/PyFunc', defined at:
File "train/train.py", line 222, in
train()
File "train/train.py", line 137, in train
loss_weights=[0.2, 0.2, 1.0, 0.2])
File "train/../libs/nets/pyramid_network.py", line 547, in build
refined_box_lw=loss_weights[2], refined_cls_lw=loss_weights[3])
File "train/../libs/nets/pyramid_network.py", line 435, in build_losses
roi_encoder(gt_boxes, rois, num_classes, scope='ROIEncoder')
File "train/../libs/layers/wrapper.py", line 58, in roi_encoder
[tf.float32, tf.float32, tf.float32])
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/script_ops.py", line 212, in py_func
input=inp, token=token, Tout=Tout, name=name)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_script_ops.py", line 50, in _py_func
"PyFunc", input=input, token=token, Tout=Tout, name=name)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 2956, in create_op
op_def=op_def)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1470, in init
self._traceback = self._graph._extract_stack() # pylint: disable=protected-accessInvalidArgumentError (see above for traceback): exceptions.ValueError: could not broadcast input array from shape (4) into shape (0)
[[Node: pyramid_2/ROIEncoder/PyFunc = PyFunc[Tin=[DT_FLOAT, DT_FLOAT, DT_INT32], Tout=[DT_FLOAT, DT_FLOAT, DT_FLOAT], token="pyfunc_13", _device="/job:localhost/replica:0/task:0/device:CPU:0"](random_shuffle_queue_Dequeue:3, pyramid_1/SampleBoxes/Reshape/_929, pyramid_2/ROIEncoder/PyFunc/input_2)]]
Please help me to check it, thanks.
Traceback (most recent call last):
File "/home/zzz/FastFPN/unit_test/resnet50_test.py", line 66, in
mask_lw=0.2)
TypeError: build_losses() got multiple values for keyword argument 'num_classes'
函数定义是只有9个变量,那一行代码确实有11个变量。emmm这个该怎么改
loss, losses, batch_info = pyramid_network.build_losses(pyramid, outputs,
gt_boxes, gt_masks,
num_classes=81, base_anchors=9,
rpn_box_lw =0.1, rpn_cls_lw = 0.2,
refined_box_lw=2.0, refined_cls_lw=0.1,
mask_lw=0.2)
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.