Sicily-F
Sicily-F
hi - did you figure this issue out? I'm wondering if either of you has used the model on a Window's operating system? I've opened a new issue here: https://github.com/knazeri/edge-connect/issues/168
hi there, I've experienced a similar issue - am watching this thread
can i ask, did you have issues performing the pixel randomisation? Or did you use the grey/black squares for the random erasing
hi again- any chance you could check out my question here: https://github.com/yu4u/cutout-random-erasing/issues/6 I've still not had a reply from the owner of this repo
did anyone have issues performing the pixel randomisation?
hi again- any chance you could check out my question here: https://github.com/yu4u/cutout-random-erasing/issues/6 I've still not had a reply from the owner of this repo
Hello! Ah ok, that makes so much sense, I didn't pick up on that. THANK YOU! Success ![Uploading image.png…]()
Perhaps I am misunderstanding, but I have been running a multiclass classification model and using the following precision and recall metrics: `model.compile(loss='categorical_crossentropy', optimizer=opt, metrics=['acc',tf.keras.metrics.Precision(),tf.keras.metrics.Recall()])` One thing I am having trouble...
Hi! I tried some other models on my own photos, and they also didn't perform too well
hi there, can I just ask were you testing on your own data, or on ImageNet?