Skip to content

Problem with imagenet dataset #3

@L-ED

Description

@L-ED

Hi everyone, when i'm trying to launch provided in readme python command, i'm catching error

(mx_quant) root@226a37f8fc1a:/workspace/quantization/quant_mxnet/examples# python simulate_quantization.py --model=mobilenet1.0

************************* Settings *************************
model : mobilenet1.0
print_model : False
list_models : False
use_gpu : -1
dataset : imagenet
use_gn : False
batch_norm : False
use_se : False
last_gamma : False
merge_bn : False
weight_bits_width : 8
input_signed : false
input_bits_width : 8
quant_type : layer
num_workers : 4
batch_size : 128
num_sample : 5
quantize_input_offline : False
calib_mode : naive
calib_epoch : 3
disable_cudnn_autotune : False
eval_per_calib : False
exclude_first_conv : true
fixed_random_seed : 7
wino_quantize : none


************************* Exclude blocks *************************
mobilenet0_conv0
mobilenet0_batchnorm0


Traceback (most recent call last):
File "/workspace/quantization/quant_mxnet/examples/simulate_quantization.py", line 273, in
eval_dataset = dataset(train=False).transform_first(eval_transformer)
File "/opt/conda/envs/mx_quant/lib/python3.9/site-packages/gluoncv/data/imagenet/classification.py", line 29, in init
super(ImageNet, self).init(root=root, flag=1, transform=transform)
File "/opt/conda/envs/mx_quant/lib/python3.9/site-packages/mxnet/gluon/data/vision/datasets.py", line 300, in init
self._list_images(self._root)
File "/opt/conda/envs/mx_quant/lib/python3.9/site-packages/mxnet/gluon/data/vision/datasets.py", line 306, in _list_images
for folder in sorted(os.listdir(root)):
FileNotFoundError: [Errno 2] No such file or directory: '/root/.mxnet/datasets/imagenet/val'

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions