cannot resume model for training

[gleefeng]

I use the test ：
python compress_classifier.py -a preact_resnet20_cifar --lr 0.1 -p 50 -b 128 ../../../data.cifar10/ -j 1 --resume ../../../data.cifar10/models/best.pth.tar --epochs 200 --compress=../quantization/preact_resnet20_cifar_pact.yaml --out-dir="logs/" --wd=0.0002 --vs=0

some error：

=> loading checkpoint ../../../data.cifar10/models/best.pth.tar
Checkpoint keys:
arch
        compression_sched
        epoch
        optimizer
        state_dict
        quantizer_metadata
        best_top1
   best top@1: 39.310
Loaded compression schedule from checkpoint (epoch 0)
Loaded quantizer metadata from the checkpoint
{'params': {'bits_weights': 3, 'bits_activations': 4, 'quantize_bias': False, 'bits_overrides': OrderedDict([('conv1', OrderedDict([('wts', None), ('acts', None)])), ('layer1.0.pre_relu', OrderedDict([('wts', None), ('acts', None)])), ('final_relu', OrderedDict([('wts', None), ('acts', None)])), ('fc', OrderedDict([('wts', None), ('acts', None)]))])}, 'type': <class 'distiller.quantization.clipped_linear.PACTQuantizer'>}
Traceback (most recent call last):
  File "compress_classifier.py", line 686, in <module>
    main()
  File "compress_classifier.py", line 244, in main
    model, chkpt_file=args.resume)
  File "D:\pytorchProject\distiller\apputils\checkpoint.py", line 117, in load_checkpoint
    quantizer = qmd['type'](model, **qmd['params'])
TypeError: __init__() missing 1 required positional argument: 'optimizer'

how to fix it？

[TonightGo]

Hi, gleefeng, I got the following error when I ran the command "python3 compress_classifier.py --arch simplenet_cifar ../../../data.cifar10 -p 30 -j=1 --lr=0.01":

2018-10-22 17:03:03,745 - Log file for this run: /home/project/compress/distiller-master/examples/classifier_compression/logs/2018.10.22-170303/2018.10.22-170303.log
2018-10-22 17:03:03,745 - Number of CPUs: 24
2018-10-22 17:03:03,850 - Number of GPUs: 8
2018-10-22 17:03:03,850 - CUDA version: 8.0.61
2018-10-22 17:03:03,850 - CUDNN version: 7102
2018-10-22 17:03:03,851 - Kernel: 4.4.0-98-generic
2018-10-22 17:03:03,851 - Python: 3.5.2 (default, Nov 23 2017, 16:37:01)
[GCC 5.4.0 20160609]
2018-10-22 17:03:03,851 - PyTorch: 0.4.0
2018-10-22 17:03:03,851 - Numpy: 1.14.3
2018-10-22 17:03:03,852 - Traceback (most recent call last):
File "compress_classifier.py", line 686, in
main()
File "compress_classifier.py", line 179, in main
apputils.log_execution_env_state(sys.argv, gitroot=module_path)
File "/home/project/compress/distiller-master/apputils/execution_env.py", line 78, in log_execution_env_state
log_git_state()
File "/home/project/compress/distiller-master/apputils/execution_env.py", line 56, in log_git_state
repo = Repo(gitroot, search_parent_directories=True)
File "/home/project/compress/distiller-master/env/lib/python3.5/site-packages/git/repo/base.py", line 168, in init
raise InvalidGitRepositoryError(epath)
git.exc.InvalidGitRepositoryError: /home/project/compress/distiller-master

2018-10-22 17:03:03,852 -
2018-10-22 17:03:03,852 - Log file for this run: /home/project/compress/distiller-master/examples/classifier_compression/logs/2018.10.22-170303/2018.10.22-170303.log

Do you have this issue?

[gleefeng]

You can git clone this project to solve this problem. some git messages must be checked by execution_env.py

[nzmora]

Hi @gleefeng ,

Unfortunately resuming from a quantization session is not supported currently. See #21 (comment).

Cheers,
Neta

[TonightGo]

You can git clone this project to solve this problem. some git messages must be checked by execution_env.py

Yeah, it's ok, thank you!

[hustzxd]

I encountered the same problem:dog: I just want to evaluate the accuracy of quantized model.
Temporary modification:
quantizer.py:87

        # if train_with_fp_copy and optimizer is None:
        #     raise ValueError('optimizer cannot be None when train_with_fp_copy is True')

class WRPNQuantizer(Quantizer):

    def __init__(self, model, optimizer=None, bits_activations=32, bits_weights=32, bits_overrides=OrderedDict(),
                 quantize_bias=False):

[guyjacob]

@hustzxd the workaround you detail indeed works, thanks for posting here.
We'll work on a more permanent solution.

[stvreumi]

Hmmm...I also have problem here.
The quantized checkpoint can't be loaded for summary and testing, and the error message is the same.

[guyjacob]

We'll track this on #185, closing this one.