ZHR1997

how to train centermask2 on own datasets

13

If I want to train on the coco training set I generated, where do I need to modify the code? (Such as category number, category name, etc.)

onnx->TensorFlow BatchNormalization@0' is not a valid scope name

5

import onnx from onnx_tf.backend import prepare onnx_model = onnx.load("ch_mobile_infer_clipChanged.onnx") tf_rep = prepare(onnx_model) Traceback (most recent call last): File "", line 1, in File "/zhr/onnx-tensorflow/onnx_tf/backend.py", line 66, in prepare return cls.onnx_model_to_tensorflow_rep(model,...

lstm pytorch->onnx->rknn(rknn1.6)load onnx fail!!!

4

pytorch中lstm的代码如下： self.rnn = nn.LSTM(nIn, nHidden, num_layers=1, bidirectional=True) 能够成功转换到onnx，但是在onnx转到rknn的时候fail，代码如下  报错如下：  通过Netron查看onnx该层的结构图如下：  我猜想会不会是sequence_lens参数没有导致的？如果是的话，要如何对代码进行修改呢？如果不是的话，又是什么原因导致这个问题的出现，要如何去修改？

When I train my own data, I set rand_crop to false. Then when the trained model is tested on the training set, there is no box on the output image,...