verigle
verigle
I convert to onnx model from .pt model you provided,but when inference on opencv, has an error: > self.model = cv2.dnn.readNetFromONNX(onnx_path) > cv2.error: OpenCV(4.2.0) /io/opencv/modules/dnn/include/opencv2/dnn/dnn.inl.hpp:349: error: (-204:Requested object was not...
hi In your paper , you prelong train for 1000 epochs for submittion on kitti, is the 200 epochs for 0.001 , and last 800 epochs for 0.0001?
` fe_1 = output[::2] fe_2 = output[1::2] feature = np.hstack((fe_1, fe_2)) `
Traceback (most recent call last): File "D:/Users/acer/PycharmProjects/DispNet-TensorFlow/DispNet.py", line 419, in main() File "D:/Users/acer/PycharmProjects/DispNet-TensorFlow/DispNet.py", line 318, in main with open(GT_DIR) as f: FileNotFoundError: [Errno 2] No such file or directory: 'datasets/gopro.pkl'
File "/home/i/PycharmProjects/DispNet-TensorFlow/DispNet.py", line 421, in main() File "/home/i/PycharmProjects/DispNet-TensorFlow/DispNet.py", line 383, in main input_one_image = _norm(np.reshape(input_one_image, (1, IMAGE_SIZE_Y, IMAGE_SIZE_X, 3))) File "/home/i/.conda/envs/tensorflowcp27/lib/python2.7/site-packages/numpy/core/fromnumeric.py", line 232, in reshape return _wrapfunc(a, 'reshape', newshape, order=order)...
The bottleneck in resnet50,101 is consist of 1x1, 3×3,1×1,but why you use two 3×3 instead it in your code? The sequential of bottleneck is also different, you use BN ->conv->prelu->BN,...
### 请认真检查以下清单中的每一项 - [x] 已经搜索过,没有发现类似issue - [x] 已经搜索过文档,没有发现相关内容 - [x] 已经尝试使用过最新版,问题依旧存在 - [x] 使用的是官方版本(未替换及修改过安装目录程序文件) ### 软件版本 0.20.12 ### 操作系统 Windows x64 ### 系统版本 windows 10 ### 问题描述 TUN 模式下出现无法访问google 的问题...