-
The README suggests that we should be able to train on VOC2011 just by downloading the dataset and running train.py. Is it really the case? My training seems to converge for the first few epochs, but …
-
**Describe the bug**
I'm trying to create a Stop Limit order (`ORDER_TYPE_STOP_LOSS_LIMIT `) but i'm getting errors, one time its `LOT_SIZE ` and sometimes it's the other ones.
The problem is tha…
bixty updated
3 years ago
-
What is the ideal loss value for `darkflow` during training?
Because there is no option to evaluate loss on a validation set, knowing this value should be useful.
Is it similar to this repository?…
-
How to trade futures in:
POST /openApi/swap/v2/trade/order
Should I specify the stop loss and target when placing the order?
-
This is more of a question rather than an issue. I've noticed that while only training the heads of the network the training and validation loss decreases and plateaus after a certain number of epochs…
-
I'm training various custom neural networks and I'm getting decent results. But I often feel the need to conditionally stop training before overfitting by looking at loss, val_loss, acc and val_acc et…
-
early_stopping_hook = tf.contrib.estimator.stop_if_no_decrease_hook(
estimator=estimator,
metric_name='loss',
max_steps_without_decrease=num_train_steps,
…
ghost updated
4 years ago
-
**Describe the bug**
If a derivation logs too fast before exiting, it is cut off. This removes the last lines, which tend to contain important information about the failure.
**Steps To Reprodu…
-
Hi, I am training a conditional GAN.
At the beginning, both G and D loss decrease, but around 200 epoch, G loss start to increase from 1 to 3, and the image quality seems to stop improve.
Any idea…
-
**Describe the bug**
Hello, for a long time I've been encountering a problem with version 2.7 and the new 3.0 beta. If I shut down the system without stopping the services using the command bbb-conf …