Allen-lz comments

Results 11 comments of


                                            Allen-lz

When running train.py code,the code be terminated with no error message

tf.app.flags.DEFINE_boolean('restore', True, '') set the 'True' to 'False',and you can run

有关OU-MVLP数据集的训练

> 您好，请问可以分享下在OUMVLP数据集上训练的模型吗，自己显卡比较垃圾。。 > 邮箱：[[email protected]](mailto:[email protected])

pid_list = np.load(pid_fname)，TypeError: _reconstruct: First argument must be a sub-type of ndarray

你好作者，上述问题我已经解决了，重写了一个CASIA-B_73_False.npy文件。接下来出现了以下错误： Initialzing... Initializing data source... Loading training data... Data initialization complete. Initializing model... Model initialization complete. Training START Traceback (most recent call last): File "train.py", line 21, in m.fit()...

pid_list = np.load(pid_fname)，TypeError: _reconstruct: First argument must be a sub-type of ndarray

多次打扰很抱歉。RuntimeError: CUDA eor: out of memory确实是Pytorch版本的原因导致

pid_list = np.load(pid_fname)，TypeError: _reconstruct: First argument must be a sub-type of ndarray

感谢作者在百忙之中抽时间回答问题，我的是11g的卡，用Pytorch1.0刚刚好按照batch_size=(8,16)满显存运行，问题已经解决。

Shape's jaw fit abnormally

> > Hello，thanks for your interest. > > Maybe the wrong 3D keypoints are used when calculating ‘trans_base_2_camera’ (function 'get_trans_base_to_camera') in step2*.py. You can test the following 3D keypoints: >...

Some questions about the prepare_cvact.py

I re-executed the data processing and found that an error occurred during the process of decompressing ANU_data_small.tar.gz. This resulted in a data set that was too small. ` tar: Skipping...

Some questions about the prepare_cvact.py

oh~, thank you very much for your prompt reply, I will also try it again.