FCInter

RuntimeError: Backward is not reentrant

4

I compile the project and run the test.py. I got the error ``` RuntimeError: Backward is not reentrant, i.e., running backward with same input and grad_output multiple times gives different...

TypeError: '_Stat' object does not support indexing

1

I'm running the code on a server. However, when I run the `init.sh`, I received the following error messages. What's wrong with the code? I'm using python 2.7 and mxnet-1.2.1....

cannot get good training result

2

I try to train the model from the very beginning. I downloaded the models and put them as following ``` ./model/pretrained_model/resnet_v1_101-0000.params ./model/pretrained_model/flownet-0000.params ``` Then I started the training using the...

Why is the test network different from the training network?

20

I read the code and find that, the training and the test networks are different in structure. In particular, in training network, the embedding layers are added after the concatenation...

I'm running the [tutorial](https://github.com/open-mmlab/mmtracking/blob/master/demo/MMTracking_Tutorial.ipynb). It works but I cannot get the predicted label for each box. I can only get the object_id, bbox, and confidence score in the tracking result,...

CMake Error at /usr/lib/x86_64-linux-gnu/cmake/Boost-1.71.0/BoostConfig.cmake:117 (find_package):

1

I follow the installation tutorial [here](https://colmap.github.io/install.html). I finished the `sudo apt-get install` and finished the following steps: ``` git clone https://github.com/colmap/colmap.git cd colmap mkdir build cd build ``` I failed...

keras_nlp.models.from_preset gets Segmentation fault (core dumped)

1

I'm using keras_nlp and I get Segmentation fault (core dumped) in the following code: ``` import os os.environ["KERAS_BACKEND"] = "torch" # "jax" or "tensorflow" or "torch" import keras_nlp import keras_core...

怎么把语义分割的标注改成实例分割呢？

1

如题。 标完一批图片了突然发现想做实例分割。求助T.T

The tf.control_dependencies seems extremely time consuming

3

试着运行了好几次，感觉很卡啊。每次执行到tf.control_dependencies的时候就会卡很久，最长的能卡15分钟左右。求问是什么原因啊？是因为网络太大了吗？我看tf.control_dependencies那里，变量列表长度是2300多，变量太多导致的嘛？ 网络构建完以后，要送入GPU执行的时候，也是卡住，十几分钟了还没开始运行。 有什么办法能加速一下嘛？感谢大佬指点！ I run the train_search.py for multiple times. The program always hang at the `tf.control_dependencies` in the compute_unrolled_step() function. It just stops here and printing nothing. Specifically, it...

How to load images of different format into the same data format

3

I'm trying to implement a training project by myself on webvision data 2.0. I find that there are in total 11 image formats, namely `jpg, jpeg, png, gif, bmp, tif,...