kinetics-i3d
kinetics-i3d copied to clipboard
deepmind
Ideas to improve the training accuracy
I am trying to fine-tune the model with UCF-101 dataset. with the SGD optimizer and lr decay, I can get almost 91.79% accuracy after 6000 steps with BS: 32.
global_step = tf.Variable(0, trainable=False)
learning_rate = tf.compat.v1.train.exponential_decay(3, global_step, 100, 0.96)
optimizer = tf.compat.v1.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step)
From the paper, I see the accuracy could be 94.x%, any ideas to improve my accuracy?
How many frames are being used in training and testing ?
Joao
On Wed, Feb 12, 2020 at 2:45 PM Leslie-Fang [email protected] wrote:
I am trying to fine-tune the model with UCF-101 dataset. with the SGD optimizer and lr decay, I can get almost 91.79% accuracy after 6000 steps with BS: 32.
global_step = tf.Variable(0, trainable=False) learning_rate = tf.compat.v1.train.exponential_decay(3, global_step, 100, 0.96) optimizer = tf.compat.v1.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step)
From the paper, I see the accuracy could be 94.x%, any ideas to improve my accuracy?
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/deepmind/kinetics-i3d/issues/93?email_source=notifications&email_token=ADXKU2X7VJIO5B3X5FBGE6TRCQDSNA5CNFSM4KT3DOC2YY3PNVWWK3TUL52HS4DFUVEXG43VMWVGG33NNVSW45C7NFSM4IM6WIKA, or unsubscribe https://github.com/notifications/unsubscribe-auth/ADXKU2QV7URPHTL7SC4A4ADRCQDSNANCNFSM4KT3DOCQ .
@joaoluiscarreira Thanks for looking into my issue. Training: almost 9500 frame in one epoch. Testing: almost 3700 frame. BTW: I am using depth 64.
Let me clarify: what we did was to use 64 frames in training and 250 frames in testing. If you're testing on only 64 frames for each video that would have a negative impact.
Joao
On Wed, Feb 12, 2020 at 2:50 PM Leslie-Fang [email protected] wrote:
@joaoluiscarreira https://github.com/joaoluiscarreira Thanks for looking into my issue. Training: almost 9500 frame in one epoch. Testing: almost 3700 frame. BTW: I am using depth 64.
— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/deepmind/kinetics-i3d/issues/93?email_source=notifications&email_token=ADXKU2QYY3IPL3ZFJ2WPWK3RCQECZA5CNFSM4KT3DOC2YY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOELRBHMQ#issuecomment-585241522, or unsubscribe https://github.com/notifications/unsubscribe-auth/ADXKU2VMJL7D5ZHYW3WMNP3RCQECZANCNFSM4KT3DOCQ .
我正在尝试使用 UCF-101 数据集微调模型。 使用 SGD 优化器和 lr 衰减，在 BS: 32 的 6000 步后，我可以获得几乎 91.79% 的准确率。
global_step = tf.Variable(0, trainable=False) learning_rate = tf.compat.v1.train.exponential_decay(3, global_step, 100, 0.96) optimizer = tf.compat.v1.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step)从论文中，我看到准确率可能是 94.x%，有什么想法可以提高我的准确率吗？
Can I share the code？
