Size mismatch error on Resnet at quantization stage

[pgadosey]

Hi,
Trying TTQ on RESNET18 but getting a runtime error. Can't seem to find what the issue is:

/home/user2/Desktop/pttq/resnet_caltech/trained-ternary-quantization-master/utils/training.pyc in train(model, loss, optimization_step_fn, train_iterator, val_iterator, n_epochs, patience, threshold, lr_scheduler)
53
54 batch_loss, batch_accuracy, batch_top5_accuracy = optimization_step_fn(
---> 55 model, loss, x_batch, y_batch
56 )
57 running_loss += batch_loss

in optimization_step_fn(model, loss, x_batch, y_batch)

/home/user2/Desktop/pttq/resnet_caltech/trained-ternary-quantization-master/utils/quantization.py in optimization_step(model, loss, x_batch, y_batch, optimizer_list, t)
94
95 # get modified grads
---> 96 k_fp_grad, w_p_grad, w_n_grad = get_grads(k.grad.data, k_fp.data, w_p, w_n, t)
97
98 # grad for full precision kernel

/home/user2/Desktop/pttq/resnet_caltech/trained-ternary-quantization-master/utils/quantization.py in get_grads(kernel_grad, kernel, w_p, w_n, t)
39 c = torch.ones(kernel.size()).cuda() - a - b
40 # scaled kernel grad and grads for scaling factors (w_p, w_n)
---> 41 return w_pakernel_grad + w_nbkernel_grad + 1.0ckernel_grad,
42 (akernel_grad).sum(), (bkernel_grad).sum()
43

/usr/local/lib/python2.7/dist-packages/torch/tensor.pyc in mul(self, other)
319
320 def mul(self, other):
--> 321 return self.mul(other)
322 rmul = mul
323

RuntimeError: invalid argument 3: sizes do not match at /pytorch/torch/lib/THC/generated/../generic/THCTensorMathPointwise.cu:351

[pgadosey]

using the classifier weights as the parameter group to be quantized, i do not have this error but the focus is to quantize the conv and downsample layers which gives the above error when i attempt training

[pgadosey]

Found my error. Thanks