-
Notifications
You must be signed in to change notification settings - Fork 73
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
add model codes about PSMNet #52
base: master
Are you sure you want to change the base?
Conversation
@@ -0,0 +1,304 @@ | |||
import tensorflow as tf | |||
import tensorflow.keras as keras | |||
from .utils import * |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
What are you trying to import here?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
line 3 should be deleted.
with tf.compat.v1.variable_scope('conv0',reuse=reuse): | ||
if reuse == tf.compat.v1.AUTO_REUSE: | ||
tf.print(bottom, ['left_batch_size:',bottom]) | ||
self._add_to_layers('CNN/conv0/conv0_1', sharedLayers.conv2d(bottom, [3, 3, 3, 32], \ |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
you can set the shape of the filter to [3, 3, input_batch.get_shape()[-1].value, 32] to handle inputs with a number of channels different from 3
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
line 70 has been changed to the following:
self._add_to_layers('CNN/conv0/conv0_1', sharedLayers.conv2d(bottom, [3, 3, bottom.get_shape()[-1].value, 32],
activation=tf.nn.leaky_relu, batch_norm=True, apply_relu=True,strides=2, name='conv0_1',reuse=reuse))
The same error.
I try to train on scene_flow dataset. the train script is the following:
CUDA_VISIBLE_DEVICES=4 python Train.py --trainingSet=/host/nfs/hs/scene_flow/train.list --validationSet=/host/nfs/hs/scene_flow/val.list --output=_output_PSMNet --modelName=PSMNet --imageShape 256 512 --batchSize=1 --numEpochs=10