simple-faster-rcnn-pytorch
simple-faster-rcnn-pytorch copied to clipboard
chenyuntc
A simplified implemention of Faster R-CNN that replicate performance from origin paper
Please I have written the following code for translating sign language translation to text, previously it was working but it brings this value error. "ValueError: object __array__ method not producing...
/simple-faster-rcnn-pytorch-master/model/utils/creator_tool.py", line 429, in __call__ roi = roi[keep] ValueError: object **____array**____****method not producing an array **the code is here**and I dont know how to solve this problem 1. # Apply...
The problem is about skimage > File "data/dataset.py", line 67, in preprocess img = sktsf.resize(img, (C, H * scale, W * scale), mode='reflect',anti_aliasing=False) TypeError: resize() got an unexpected keyword argument...
I want to set a bigger value of batch size,but it can not work when i change the value,it seems the value can only be 1.How can i set a...
Hi, I have a question about structure of Faster R-CNN. Why should we use two localization outputs from RPN and Classification Head? I think only localization results from RPN is...
when i see generate_anchors process,I found that the axis of ancher for example:[-100 -100 120 120](x,y,height,width). so why the axis of ancher is negetive integer???
Traceback (most recent call last): File "/media/chen/文档/qindengda1/simple-faster-rcnn-pytorch-master/train.py", line 130, in fire.Fire(train) File "/home/chen/anaconda3/envs/qindd/lib/python3.5/site-packages/fire/core.py", line 138, in Fire component_trace = _Fire(component, args, parsed_flag_args, context, name) File "/home/chen/anaconda3/envs/qindd/lib/python3.5/site-packages/fire/core.py", line 468, in _Fire...
Thanks for your sharing! It helps me a lot. And I have 2 question about "./model/utils/bbox_tools.py". 1. In "./model/utils/bbox_tools.py": ``` import numpy as np import numpy as xp ... ```...
root@52f54a48a085:/home/simple-faster-rcnn-pytorch# python train.py train --env='fasterrcnn-caffe' --plot-every=100 --caffe-pretrain=False /home/simple-faster-rcnn-pytorch/model/utils/nms/non_maximum_suppression.py:12: UserWarning: the python code for non_maximum_suppression is about 2x slow It is strongly recommended to build cython code: `cd model/utils/nms/; python3 build.py...
RuntimeError: Legacy autograd function with non-static forward method is deprecated. Please use new-style autograd function with static forward method. (Example: https://pytorch.org/docs/stable/autograd.html#torch.autograd.Function) 升级了torch和torchvision版本，又降低了torch和torchvision版本都不行 求解决办法
