jsjs0827

train my data with pva（2 categories）

4

@sanghoon dear sanghoon,I got a problem in training my own data with your pva-frcnn.When I use example_train_384,my modification: train.prototxt line11 num_classes : 21 to 2 line6511 num_output84 to 8(When I...

something about small dataset for finetuning?

2

How did you do the project? Can you give me a way to contact you for more details. I just doubt about finetune the network with only 6 pictures.What leads...

import error

9

In Ubuntu 16.04 LTS，cmake,make and setup are all done. python import ncnn ModuleNotFoundError: No module named 'ncnn.ncnn'. What should I do?

something wrong with /usr/lib/python2.7/json/decoder.py

1

Using Tensorflow 1.1.0 ``` Traceback (most recent call last): File "/data/siamfc-tf/siamfc-tf-master/run_tracker_evaluation.py", line 174, in sys.exit(main()) File "/data/siamfc-tf/siamfc-tf-master/run_tracker_evaluation.py", line 16, in main hp, evaluation, run, env, design = parse_arguments() File "/data/siamfc-tf/siamfc-tf-master/src/parse_arguments.py",...

something wrong in running the demo.py

3

When I run the demo.py: File "./tools/demo.py", line 11, in from networks.factory import get_network File "/home/amax/JS/tflearningjs/tffasterrcnn/Faster-RCNN_TF-master/tools/../lib/networks/__init__.py", line 8, in from .VGGnet_train import VGGnet_train File "/home/amax/JS/tflearningjs/tffasterrcnn/Faster-RCNN_TF-master/tools/../lib/networks/VGGnet_train.py", line 2, in from networks.network...

cv2.error:

1

pytorch1.7.1 cv2 4.3.0 win10 I download the yolov5s.pth then I run the convert_onnx.py,the onnx file ran normally,but in the end of convert_onnx.py dnnnet = cv2.dnn.readNet(output_onnx) failed:error: (-212:Parsing error) Input node...

About train the model from scratch.

1

Sorry to bother you. I turn your code to pytorch,and I retrain the wpod from scratch, but it just cannot converge.Can you give me some advice?

Sorry to bother you. I am new to matconv,maybe I make some low mistakes, I really want to get some help from you. When I ran the train_id_net_res_market_new.m, it collapsed:...

Something about the label

2

I see the MSCNN\mscnn-master\examples\kitti_car\mscnn-7s-384-2x trainval_1st.protxotxt,the label top: "label_1_5x5" top: "label_1_7x7" top: "label_2_5x5" top: "label_2_7x7" top: "label_3_5x5" top: "label_3_7x7" top: "label_4_5x5" so many label for just one picture?