Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
ModelZoo
ResNet50_tensorflow
Commits
461e88f2
Commit
461e88f2
authored
Jan 26, 2022
by
A. Unique TensorFlower
Browse files
Internal change
PiperOrigin-RevId: 424505240
parent
17b3db9f
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
63 additions
and
0 deletions
+63
-0
official/vision/beta/configs/experiments/image_classification/imagenet_mobilenetv3small_tpu.yaml
...s/image_classification/imagenet_mobilenetv3small_tpu.yaml
+63
-0
No files found.
official/vision/beta/configs/experiments/image_classification/imagenet_mobilenetv3small_tpu.yaml
0 → 100644
View file @
461e88f2
# MobileNetV3Small ImageNet classification. 67.5% top-1 and 87.6% top-5 accuracy.
runtime
:
distribution_strategy
:
'
tpu'
mixed_precision_dtype
:
'
bfloat16'
task
:
model
:
num_classes
:
1001
input_size
:
[
224
,
224
,
3
]
backbone
:
type
:
'
mobilenet'
mobilenet
:
model_id
:
'
MobileNetV3Small'
filter_size_scale
:
1.0
norm_activation
:
activation
:
'
relu'
norm_momentum
:
0.997
norm_epsilon
:
0.001
use_sync_bn
:
false
dropout_rate
:
0.2
losses
:
l2_weight_decay
:
0.00001
one_hot
:
true
label_smoothing
:
0.1
train_data
:
input_path
:
'
imagenet-2012-tfrecord/train*'
is_training
:
true
global_batch_size
:
4096
dtype
:
'
bfloat16'
validation_data
:
input_path
:
'
imagenet-2012-tfrecord/valid*'
is_training
:
false
global_batch_size
:
4096
dtype
:
'
bfloat16'
drop_remainder
:
false
trainer
:
train_steps
:
312000
# 1000 epochs
validation_steps
:
12
validation_interval
:
312
steps_per_loop
:
312
# NUM_EXAMPLES (1281167) // global_batch_size
summary_interval
:
312
checkpoint_interval
:
312
optimizer_config
:
optimizer
:
type
:
'
rmsprop'
rmsprop
:
rho
:
0.9
momentum
:
0.9
epsilon
:
0.002
learning_rate
:
type
:
'
exponential'
exponential
:
initial_learning_rate
:
0.01
decay_steps
:
936
# 3 * steps_per_epoch
decay_rate
:
0.99
staircase
:
true
ema
:
average_decay
:
0.9999
trainable_weights_only
:
false
warmup
:
type
:
'
linear'
linear
:
warmup_steps
:
1560
warmup_learning_rate
:
0.001
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment