appleleaves
appleleaves
It seems the author separate it with a simply cut with a mean value, matlab code run_cifar10.m: line 61,62
I can only reach about 65% training ResNet | FP weights, FP activations | 100 I used 8 cards and simply ran the code. Would you like to share some...
I run the experiments by using command `lqz TrainR2B` Errors ocurr as: ``` Traceback (most recent call last): File ".../lqz", line 5, in from larq_zoo.experiments import cli ModuleNotFoundError: No module...
Thanks for your advice! The code is working.
When I run the code using `lqz TrainR2B`, it appeared `killed` with no signal. Any ideas why it happens?
The R2B training has 4 stages, how can I resume it from, for example finishing the first stage?
I follow the `"lqz TrainR2B initial_stage=1 stage_1.initialize_teacher_weights_from="/home/yourname/some/dir/models/resnet_fp"" ` but it seem like there is some bugs! I then fix it by changing code in "larq_zoo/training/knowledge_distillation/multi_stage_training.py (lines bottom)" into ``` def...
@XinDongol Would you like to share the python models directory code for the ResNet-XNOR or share the implementation idea?
1.make matcaffe in the caffe root , 2.if fail, reboot your machine and try again 3.fail again? sorry, I don't know
You may try using this https://docs.larq.dev/larq/.