PocketFlow
PocketFlow copied to clipboard
Tencent
An Automatic Model Compression (AutoMC) framework for developing smaller and faster AI applications.
您好，我无论在resnet还是mobilenet上，利用dcp通道剪枝后，模型大小始终不变，即使转成.pb文件也不变，但是模型测试相比原来有变化，请问这是什么原因呢
当我用--learner=chn-pruned-rmt \ --cpr_prune_ratio=0.40 压缩自定义模型的时候，发现无论我设置的cpr_prune_ratio为多少，最后压缩完成的模型的参数量都是一样的。
**Describe the bug** @jiaxiang-wu The compressed model with `ChannelPrunedRmtLearner` cannot be converted to .pd or .tflite file using `tools/conversion/export_chn_pruned_tflite_model.py` or `tools/conversion/export_pb_tflite_models.py`. **To Reproduce** Steps to reproduce the behavior: 1. I...
I use a NCHW model as input for channel_pruning_rmt and change the corresponding index of tensors. However, I fail at "assert err_full < 1e-6, 'unable to recover output feature maps...
1. horovod HOROVOD_GPU_ALLREDUCE=NCCL pip install --no-cache-dir horovod 2. Open MPI 3.0.4 no 2.1.1 wget http://www.open-mpi.org/software/ompi/v2.1/downloads/openmpi-2.1.1.tar.gz tar xzvf openmpi-2.1.1.tar.gz WORKDIR openmpi-2.1.1 ./configure make -j48 sudo make install sudo ldconfig which mpicc...
File "/opt/project/learners/uniform_quantization/learner.py", line 92, in __init__ self.__build_train() # for train File "/opt/project/learners/uniform_quantization/learner.py", line 193, in __build_train images.set_shape((FLAGS.batch_size, images.shape[1], images.shape[2], AttributeError: 'dict' object has no attribute 'set_shape' 怎么修改尼
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/platform/app.py", line 125, in run _sys.exit(main(argv)) File "/opt/project/main.py", line 51, in main learner = create_learner(sm_writer, model_helper) File "/opt/project/learners/learner_utils.py", line 60, in create_learner learner = UniformQuantTFLearner(sm_writer, model_helper) File "/opt/project/learners/uniform_quantization_tf/learner.py", line...
When the mobilenet arch is exported the BN and RELU6 should also change. Are you planning to change this ? Also I noticed that the .pb models after the channel...
Because pruning with RL method takes long long time,I use uniform prune method. But when evaluating after pruning,I got this error Incompatible shapes: [64,1024,1,1] vs. [128,1024,1,1] error. Here is the...
I use tf.keras.layers.Conv1D in my own network, and i have trained it with FullPrecLearner. Then when I use ChannelPrunedLearner, there are some errors : ERROR:tensorflow:the number of real inputs of...
