PocketFlow
PocketFlow copied to clipboard
Tencent
An Automatic Model Compression (AutoMC) framework for developing smaller and faster AI applications.
When I use chn_prune to test the self defined model fmnist and simple cnn, when the *.pb file convert to *.tflite file, this error occurs: ` INFO:tensorflow:/home/adminusl/PocketFlow/models/model.pb generated INFO:tensorflow:/home/adminusl/PocketFlow/models/model.pb ->...
Can the compression method provided by pocketflow be applied to MASK R-CNN?
@ubuntu:~/PocketFlow$ ./scripts/run_seven.sh nets/mobilenet_at_ilsvrc12_run.py -n=8 --learner dis-chn-pruned --mobilenet_version 2 --enbl_dst creating a minimal code directory: /home/wangzhaoming/PocketFlow -> /home/wangzhaoming/PocketFlow-minimal Python script: nets/mobilenet_at_ilsvrc12_run.py Job name: pocket-flow # of GPUs: 8 extra arguments: --learner...
when I run the examples(Fashion Minist) on my server, I got below , is there any solutions? Thanks Traceback (most recent call last): File "main.py", line 30, in sess =...
https://api.ai.tencent.com/pocketflow/: This URL provides nginx not found error, required for downloading models.
InvalidArgumentError (see above for traceback): You must feed a value for placeholder tensor 'model/input_1' with dtype float and shape [?,160,240,1] [[Node: model/input_1 = Placeholder[dtype=DT_FLOAT, shape=[?,160,240,1], _device="/job:localhost/replica:0/task:0/device:GPU:0"]()]] When I run my...
**System information** - PocketFlow version: commit: 53b82cba5a34834400619e7c335a23995d45c2a6 - Doc Link: https://pocketflow.github.io/self_defined_models/ **Describe the documentation issue** In the definition of ModelHelper one positional argument is missing **data_format**: ``` class ModelHelper(AbstractModelHelper): """Model...
我在使用faster_rcnn_at_pascalvoc_run.pys的时候出现了这个错误： Traceback (most recent call last): File "main.py", line 70, in tf.app.run() File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/platform/app.py", line 125, in run _sys.exit(main(argv)) File "main.py", line 51, in main learner = create_learner(sm_writer, model_helper) File...
我看了教程都是说要先用这个训练或者finefune一个模型，然后在这个model上进行压缩，还要在配置文件里设置data路径，如果说我没有数据，但是有一个模型，可以只用压缩部分么，这样配置文件怎么写呢？对了，我这模型有faster rcnn和facenet这都支持么？