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
Hi, I am running training on SageMaker notebook instance. I made visdom running. However i cannot open the dashboard through sagemaker notebook. Is there any way to access training progress...
 对最后一维（2个数字嘛）做了softmax出来，为什么取序号为1的那列呢？是把1的那列当作包含物体的概率？为什么啊？这一点我没找到什么资料。
你好，请问训练过程中loss变化比较剧烈是什么原因呢？ 还有就是，想请教以下，如果自己把代码改成batch_size>1的情况，工程量大不大？（还没仔细看代码）
Since I have checked that module: resources are installed but the program keeps prompting ModuleNotFoundError: No module named 'resource' and I have found on StackOverflow that module resource is not...
I'll be grateful if any one can give me some suggestions about how to run the code with batchsize greater than 1
When I train this file "train.py" and the visdom.server has opened(I firstly run "python visdom.server" in the terminal and then run "python train.py" in another terminal), but I get this...
change ```python for ii, (img, bbox_, label_, scale) in tqdm(enumerate(dataloader)): ``` to ```python for ii, (img, bbox_, label_, scale) in enumerate(tqdm(dataloader)): ``` to present the progress bar
Hi Yun, I have finished the training part and got some models that look like 'fasterrcnn_01050646_0.055125557309203356'. Can I load the model for real time object detection test? Is there a...
Hello. I want to: 1- train Faster RCNN on my own custom dataset. 2- use the pre-trained Faster RCNN on the VOC2007 as the initial weights to train it then...
who can help me ? I really need help. I already opened visdom, but when I train, I meet these exception. `(simp) E:\目标检测\simple-faster-rcnn-pytorch-master>python train.py train --env='fasterrcnn-caffe' --plot-every=100 --caffe-pretrain ======user config========...
