mit-han-lab/haq
[CVPR 2019, Oral] HAQ: Hardware-Aware Automated Quantization with Mixed Precision
PythonMIT
Issues
- 0
torch version problem
#24 opened by qwerfdsadad - 4
- 6
what does the lookup table mean
#17 opened by Jonxjdong - 0
- 11
Question about linear quantization
#14 opened by frankinwi - 0
cant download checkpoint
#21 opened by cyh-ustc - 0
Performance for mixed precision Resnets?
#20 opened by kentaroy47 - 0
Training with simulated quantization
#19 opened by techmonsterwang - 0
Quantization of custom models
#18 opened by Sahil-RB - 1
fused mobilenet v1
#8 opened by HKLee2040 - 1
- 1
Linear quantization
#10 opened by H-Ginger - 0
Measurement of latency and energy
#15 opened by ChaofanTao - 1
Question about model size constraint
#12 opened by skeletondyh - 7
Regarding paper and codes
#7 opened by yzhang93 - 2
activation quantization
#9 opened by Siamw - 3
Quantizing activation
#2 opened by HKLee2040 - 0
Pretrained Mobilenet model
#5 opened by libingict - 1
How to measure model size?
#6 opened by yzhang93 - 0
quantization environment
#3 opened by HKLee2040 - 1
RuntimeError: CUDA error: out of memory
#4 opened by talenz - 0
Typo or feature?
#1 opened by greyhuman