-
I created a YOLO model using [AlexeyAB's](https://github.com/AlexeyAB/darknet) repository and set stride=4 to detect small objects to be detected as suggested in the README page.
However, when I tr…
-
## ❓ Questions and Help
Hi I am running PT XLA 1.11 built with CUDA 11.3 and CUDNN 8.2. When I run `test_train_mp_imagenet_amp.py` I get the following warning(not an error) before the program starts …
-
Hi, trying to learn spektral here. I can't seem to use ARMAConv:
def create_model(n_nodes, n_node_features, model_layers):
node_features_input = Input(shape=(n_node_features,), dtype=tf.float3…
-
剪枝后进行mnn转换，报错
Error for compute convolution shape, need channel = 62, input channel = 64
Error for compute convolution shape, need channel = 62, input channel = 64
Error for compute convolution sha…
-
As is shown in common resnet-N models，if output channels > input channels，the shortcut should be a layer with Batch Normalization. However, as is shown in the programs provided, the Batch Normalizatio…
-
-
I am a new learner and find this repo by CVPR 2016 paper.Is there any demo about temporal convolution?
The repo requires caffe.But I can't find the 4-layer 1-D temporal convolution network.
-
## error log | 日志或报错信息 | ログ
Segmentation fault (core dumped)
## model | 模型 | モデル
1. original model
Yolov5s
## how to reproduce | 复现步骤 | 再現方法
1. Download my .bin and .param file
2. Run th…
-
https://paperswithcode.com/method/depthwise-separable-convolution#:~:text=While%20standard%20convolution%20performs%20the,a%20linear%20combination%20of%20the
current setup
![Screenshot from 2024-0…
-
Hello author, I used your code for adversarial example generation. I found that in your code, the adversarial examples generated by advgan, i.e. baseline samples, have a serious checkerboard effect. H…