Comments (9)
Step 0: 9.869 sec
Training Data Eval:
accuracy: 1.00000
Validation Data Eval:
accuracy: 1.00000
Step 1: 2.662 sec
Step 2: 2.699 sec
Step 3: 2.657 sec
Step 4: 2.689 sec
Step 5: 2.695 sec
Step 6: 2.661 sec
Step 7: 2.743 sec
Step 8: 2.775 sec
Step 9: 2.694 sec
Step 10: 2.696 sec
Training Data Eval:
accuracy: 1.00000
Validation Data Eval:
accuracy: 1.00000
Step 11: 2.688 sec
Step 12: 2.844 sec
Step 13: 2.736 sec
Step 14: 2.777 sec
Step 15: 2.744 sec
Step 16: 2.784 sec
Step 17: 2.730 sec
Step 18: 2.717 sec
Step 19: 2.792 sec
Step 20: 2.677 sec
Training Data Eval:
accuracy: 1.00000
Validation Data Eval:1.000
I think we have the same problem
from c3d-tensorflow.
Try to change your batch_size?
from c3d-tensorflow.
it's 8 at first I changed it to 10 it turns out that the accuracy is still 1.00000
@binhhoangtieu
from c3d-tensorflow.
DId u solve this by changing batch_size?
@binhhoangtieu
from c3d-tensorflow.
Yes, solved with my problem because my accuracy is changed after each iteration. I'm not sure about your case.
from c3d-tensorflow.
Hello @cckenny and @binhhoangtieu ,
I get the similar error. Accuracy is always zero.
I changed the batch size as you said , but it is still 0.
I have just changed some parts of my code as following,
Have any suggestion ?
init = tf.global_variables_initializer()
# Create a saver for writing training checkpoints.
saver = tf.train.Saver(varlist1) # Edit : Add ops to save and restore only varibles without out layer using the name "varlist1"
# Create a session for running Ops on the Graph.
sess = tf.Session(
config=tf.ConfigProto(allow_soft_placement=True)
)
sess.run(init)
if os.path.isfile(model_filename) and use_pretrained_model:
saver.restore(sess, model_filename) # EDIT
print("model is restored")
The output :
.
.
.
Training Data Accuracy: 0.00000
Validation Data Accuracy: 0.00000
Step 2241: 7.663 sec
Training Data Accuracy: 0.00000
Validation Data Accuracy: 0.00000
Step 2242: 7.619 sec
Training Data Accuracy: 0.00000
Validation Data Accuracy: 0.00000
Step 2243: 7.686 sec
Training Data Accuracy: 0.00000
Validation Data Accuracy: 0.00000
Step 2244: 8.781 sec
Training Data Accuracy: 0.00000
Validation Data Accuracy: 0.00000
from c3d-tensorflow.
@cckenny @binhhoangtieu have you solved the problem? I met the same problem with you.
Step 5000: 5.591 sec
Training Data Eval:
accuracy: 1.00000
Validation Data Eval:
accuracy: 1.00000
Step 5100: 1.235 sec
Training Data Eval:
accuracy: 1.00000
Validation Data Eval:
accuracy: 1.00000
Step 5200: 1.235 sec
Training Data Eval:
accuracy: 1.00000
Validation Data Eval:
accuracy: 1.00000
from c3d-tensorflow.
@zeynepgokce : Check your input data and pre-trained model restoration
from c3d-tensorflow.
@cckenny @binhhoangtieu have you solved the problem? I met the same problem with you.
Step 5000: 5.591 sec
Training Data Eval:
accuracy: 1.00000
Validation Data Eval:
accuracy: 1.00000
Step 5100: 1.235 sec
Training Data Eval:
accuracy: 1.00000
Validation Data Eval:
accuracy: 1.00000
Step 5200: 1.235 sec
Training Data Eval:
accuracy: 1.00000
Validation Data Eval:
accuracy: 1.00000
Have you solved this problem? I can't settle this
from c3d-tensorflow.
Related Issues (20)
- Before about the reshape of dimension transform issues HOT 1
- ValueError: Cannot feed value of shape (11, 16, 160, 160, 3) for Tensor 'Placeholder:0', which has shape '(12, 16, 160, 160, 3)' HOT 1
- train_c3d_ucf101.py
- predict_c3d_ucf101.py
- very very big loss values
- Could you give me a list as example? HOT 1
- ValueError: setting an array element with a sequence. HOT 1
- What is the difference between clip accuracy and video accuracy?
- Train with last checkpoint
- ERROR when using conv3d
- about how to use .meta or index
- about preprocessing HOT 7
- ResourceExhaustedError in train_c3d_ucf101.py HOT 2
- UnboundLocalError: local variable 'img_datas' referenced before assignment HOT 2
- the accuracy is always 0 HOT 2
- overfitting HOT 1
- prototxt file for conv3d_deepnetA_sport1m_iter_1900000.caffemodel
- missunderstanding about .model file type HOT 1
- hou ge niubility HOT 1
- pi zhu is watching you
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from c3d-tensorflow.