Yazdan

PP-structure to Onnx error

6

**Please fill in the information below so that we can solve the problem quickly, Thanks !** **Describe the bug** A clear and concise description of what the bug is. I...

attention head weight shapes in paddle and pytorch model are different

1

I was able to convert the PP-structure paddle train model (best_accuracy.pdparams, best_accuracy.pdopt, best_accuracy.stated) to pytorch model (model.pth). However I realized that the model output is not the same as the...

How to convert pp-structure train model to onnx

3

I was able to convert the PP-structure paddle train model (best_accuracy.pdparams, best_accuracy.pdopt, best_accuracy.stated) to pytorch model (model.pth). How can I convert the model.pth to onnx model considering that model.pth is...

OP_REQUIRES failed

2

2021-03-19 05:40:04.139370: W tensorflow/core/framework/op_kernel.cc:1502] OP_REQUIRES failed at example_parsing_ops.cc:240 : Invalid argument: Key: global_features. Can't parse serialized Example. Traceback (most recent call last): File "/lib/python3.7/site-packages/tensorflow/python/client/session.py", line 1356, in _do_call return fn(*args)...

Save the results.

2

How to save the result in demo.py? "result = inference_detector(model, img)"

LGPMA Training Error

12

Using bash dist_train.sh I get the below error: Any clue what the root cause of the error is? ***************************************** CUDA_HOME: /usr/local/cuda-11.0 NVCC: Build cuda_11.0_bu.TC445_37.28845127_0 GCC: gcc (GCC) 8.5.0 20210514 (Red...

Opencv Error

1

I installed the opencv from source however I get this error: g++ -shared -o ./davarocr/davar_det/datasets/pipelines/lib/tp_data.so -fPIC ./davarocr/davar_det/datasets/pipelines/lib/tp_data.cpp `pkg-config --cflags --libs opencv` ./davarocr/davar_det/datasets/pipelines/lib/tp_data.cpp:23:10: fatal error: opencv2/opencv.hpp: No such file or directory...

g++

1

g++ -shared -o ./davarocr/davar_det/datasets/pipelines/lib/tp_data.so -fPIC ./davarocr/davar_det/datasets/pipelines/lib/tp_data.cpp -L/fast-drive/workspace/opencv-3.3.0/build/modules/cudabgsegm/CMakeFiles/ `pkg-config --cflags --libs opencv` /usr/bin/ld: cannot find -lopencv_cudabgsegm /usr/bin/ld: cannot find -lopencv_cudaobjdetect /usr/bin/ld: cannot find -lopencv_cudastereo /usr/bin/ld: cannot find -lopencv_cudafeatures2d /usr/bin/ld: cannot find...

In demo.py the action detection is per frame however action detection in nature is sequential task. Could you also provide a demo for temporal action detection?

What is the rational behind this formula to calculate the profit? Something does not seem right!W Why would action be a decimal number if the action space = {0, 1,...