Error in Quick start

[mmcheraghi]

Hi
Firstly, I appreciate you for this project. It seems you haven't updated your code since four years ago. Some errors occur for

python3 main_binary.py -a mobilenet --mobilenet_width 1.0 --mobilenet_input 224 --save Imagenet/mobilenet_224_1.0_w8a8 --dataset imagenet --type_quant 'PerLayerAsymPACT' --weight_bits 8 --activ_bits 8 --activ_type learned --gpus 0,1,2,3 -j 8 --epochs 12 -b 128 --save_check --quantizer --batch_fold_delay 1 --batch_fold_type folding_weights

I solved some of them by using

• transforms.Resize instead of transforms.Scale
• reader = tf.train.load_checkpoint(tensorflow_model) instead of reader = pywrap_tensorflow.NewCheckpointReader(tensorflow_model)
• correct_k = correct[:k].reshape(-1).float().sum(0) instead of correct_k = correct[:k].view(-1).float().sum(0)

I got stucked at this error:

Traceback (most recent call last):
  File "/content/training-mixed-precision-quantized-networks/main_binary.py", line 456, in <module>
    main()
  File "/content/training-mixed-precision-quantized-networks/main_binary.py", line 286, in main
    train_loss, train_prec1, train_prec5 = train(
  File "/content/training-mixed-precision-quantized-networks/main_binary.py", line 443, in train
    return forward(data_loader, model, criterion, epoch,
  File "/content/training-mixed-precision-quantized-networks/main_binary.py", line 411, in forward
    quantizer.backprop_quant_gradients()    
  File "/content/training-mixed-precision-quantized-networks/quantization/quantop.py", line 1037, in backprop_quant_gradients
    w_max_param.grad.data = grad_a_max
AttributeError: 'NoneType' object has no attribute 'data'

Can you take a look at it?

[zhen-quan]

Hi, I am also suffering from these problems, have you solved it? Thanks for replying!

[mmcheraghi]

Hi, no I couldn't solve it.

[zhen-quan]

alright.I'm learning this project and if i can run these code successfully i will come here and tell you! :)

[mmcheraghi]

Thanks a lot.

[mrusci]

I guess the error is related to the pytorch version. please follow the indication of the README (pythorch version 0.4.1) and check whether the code is working in its original stage.
unfortunately, there is no plan to upgrade the project at present