momo1986

Is it feasible to implement it on 3D Conv Layer

1

Hello, I have trained a 3D layer for image-sequence classificiation problem, the model has over 100MB parameters. I want to do pruning, how can I apply your pruning API? If...

app.py引入训练的模型checkpoint文件

2

您好，按照您的方法进行了训练，我在app.py怎么去导入之前train的模型进行对话呢？ 感谢您的分享！🙏

[Query] Is the isolation forest model for outlier detection supported now?

1

Hello, dear guys! I have an isolation forest model in Python trained. Sklearn isolation forest model and pyod isolation forest built on sklearn can both work for me. https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.IsolationForest.html?highlight=isolation%20forest#sklearn.ensemble.IsolationForest https://github.com/yzhao062/pyod/blob/master/pyod/models/iforest.py...

[Enhancement]Background concurrent copying GC freed for sklearn model constrcutor in Java

2

Hello, dear guys. Thanks for sharing. I used your transferred framework with RandomForest and ExtraTreeClassifier. It reports the memory leakage issue log. > I/zygote: Background concurrent copying GC freed 21(80KB)...

Reload my own trained model failure

3

I have my own data of speech and noise. My reproducing step: 1) ./rnnoise/src/denoise_training speech_only.raw noise_only.raw 5000000 > output.f32 2) python ./rnnoise/training/bin2hdf5.py output.f32 500000 87 training.h5 3) python ./rnnoise/training/rnn_train.py (Input:...

Error to preprocessing

2

The log is "/usr/local/miniconda3/envs/dl/bin/python: Error while finding module specification for 'squad.prepro' (ModuleNotFoundError: No module named 'squad')" I download the squad in other servers and upload to corresponding server. How to...

About the data loader

7

g = Ensemble_data_generator.ensemble_data_generator(FLAGS.train_img_dir, FLAGS.bg_img_dir, FLAGS.batch_size, FLAGS.input_size, True, True, FLAGS.augmentation_config, FLAGS.hnm, FLAGS.do_cropping) g_eval = Ensemble_data_generator.ensemble_data_generator(FLAGS.val_img_dir, FLAGS.bg_img_dir, FLAGS.batch_size, FLAGS.input_size, True, True, FLAGS.augmentation_config, FLAGS.hnm, FLAGS.do_cropping) Hello, thanks for sharing. I have three questions:...

For 21 points: The coordinate output order is thumb-tip, thumb-dip, thumb-pip, thumb-mcp, index-tip, index-dip, index-pip, index-mcp, middle-tip, middle-dip, middle-pip, middle-mcp, ring-tip, ring-dip, ring-pip, ring-mcp, pinky-tip, pinky-dip, pinky-pip, pinky-mcp and wrist....

How can two hands be recognized and posed

3

For example, I have one previous picture.  It is recognized as:  When it cut with two separated hands, OK:   It looks like that the numbers of...

Hello, my tensorflow version is 1.13rc0, keras version is 2.2.4 and opencv-version is 4.1.2. It is good when loading bigger cnn and squeezenet, but failed when loading mobilenet hdf5 file....