NotFoundError: 2 root error(s) found when trying to run the code on Tensorflow 2
eirini5th opened this issue · comments
I am using the notebook on colab and I want to run it with TF2. However, I come across this error on calling model.fit_generator:
NotFoundError:` 2 root error(s) found.
(0) Not found: Resource localhost/loss/lambda_3_loss/Variable/N10tensorflow3VarE does not exist.
[[{{node loss/lambda_3_loss/AssignAddVariableOp}}]]
[[Func/training/Adam/gradients/gradients/norm_6_1/cond_grad/StatelessIf/then/_1694/input/_4425/_2667]]
(1) Not found: Resource localhost/loss/lambda_3_loss/Variable/N10tensorflow3VarE does not exist.
[[{{node loss/lambda_3_loss/AssignAddVariableOp}}]]
0 successful operations.
0 derived errors ignored.
The problem seems to be caused by the custom loss function, since I tried using a simple dummy loss function with no errors.
The changes I've made (to no avail) are these 2:
- to include the lines
from tensorflow.python.framework.ops import disable_eager_execution disable_eager_execution()
before creating the model. Before adding these lines I came across this error:
TypeError: Cannot convert a symbolic Keras input/output to a numpy array.
This error may indicate that you're trying to pass a symbolic value to a NumPy call,
which is not supported.
Or, you may be trying to pass Keras symbolic inputs/outputs to a TF API that does not register dispatching,
preventing Keras from automatically converting the API call to a lambda layer in the Functional Model.
- to use tensorflow.keras instead of keras, after suggestions from similar github issues and stackoverflow posts.
I am also adding the custom_loss code to include a few changes I made to use TF2 instead of TF1 (basically some tf.compat.v1.* additions).
def custom_loss(y_true, y_pred):
mask_shape = tf.shape(y_true)[:4]
cell_x = tf.compat.v1.to_float(tf.reshape(tf.tile(tf.range(GRID_W), [GRID_H]), (1, GRID_H, GRID_W, 1, 1)))
cell_y = tf.transpose(cell_x, (0,2,1,3,4))
cell_grid = tf.tile(tf.concat([cell_x,cell_y], -1), [BATCH_SIZE, 1, 1, 5, 1])
coord_mask = tf.zeros(mask_shape)
conf_mask = tf.zeros(mask_shape)
class_mask = tf.zeros(mask_shape)
seen = tf.Variable(0.)
total_recall = tf.Variable(0.)
"""
Adjust prediction
"""
### adjust x and y
pred_box_xy = tf.sigmoid(y_pred[..., :2]) + cell_grid
### adjust w and h
pred_box_wh = tf.exp(y_pred[..., 2:4]) * np.reshape(ANCHORS, [1,1,1,BOX,2])
### adjust confidence
pred_box_conf = tf.sigmoid(y_pred[..., 4])
### adjust class probabilities
pred_box_class = y_pred[..., 5:]
"""
Adjust ground truth
"""
### adjust x and y
true_box_xy = y_true[..., 0:2] # relative position to the containing cell
### adjust w and h
true_box_wh = y_true[..., 2:4] # number of cells accross, horizontally and vertically
### adjust confidence
true_wh_half = true_box_wh / 2.
true_mins = true_box_xy - true_wh_half
true_maxes = true_box_xy + true_wh_half
pred_wh_half = pred_box_wh / 2.
pred_mins = pred_box_xy - pred_wh_half
pred_maxes = pred_box_xy + pred_wh_half
intersect_mins = tf.maximum(pred_mins, true_mins)
intersect_maxes = tf.minimum(pred_maxes, true_maxes)
intersect_wh = tf.maximum(intersect_maxes - intersect_mins, 0.)
intersect_areas = intersect_wh[..., 0] * intersect_wh[..., 1]
true_areas = true_box_wh[..., 0] * true_box_wh[..., 1]
pred_areas = pred_box_wh[..., 0] * pred_box_wh[..., 1]
union_areas = pred_areas + true_areas - intersect_areas
iou_scores = tf.truediv(intersect_areas, union_areas)
true_box_conf = iou_scores * y_true[..., 4]
### adjust class probabilities
true_box_class = tf.argmax(y_true[..., 5:], -1)
"""
Determine the masks
"""
### coordinate mask: simply the position of the ground truth boxes (the predictors)
coord_mask = tf.expand_dims(y_true[..., 4], axis=-1) * COORD_SCALE
### confidence mask: penelize predictors + penalize boxes with low IOU
# penalize the confidence of the boxes, which have IOU with some ground truth box < 0.6
true_xy = true_boxes[..., 0:2]
true_wh = true_boxes[..., 2:4]
true_wh_half = true_wh / 2.
true_mins = true_xy - true_wh_half
true_maxes = true_xy + true_wh_half
pred_xy = tf.expand_dims(pred_box_xy, 4)
pred_wh = tf.expand_dims(pred_box_wh, 4)
pred_wh_half = pred_wh / 2.
pred_mins = pred_xy - pred_wh_half
pred_maxes = pred_xy + pred_wh_half
intersect_mins = tf.maximum(pred_mins, true_mins)
intersect_maxes = tf.minimum(pred_maxes, true_maxes)
intersect_wh = tf.maximum(intersect_maxes - intersect_mins, 0.)
intersect_areas = intersect_wh[..., 0] * intersect_wh[..., 1]
true_areas = true_wh[..., 0] * true_wh[..., 1]
pred_areas = pred_wh[..., 0] * pred_wh[..., 1]
union_areas = pred_areas + true_areas - intersect_areas
iou_scores = tf.truediv(intersect_areas, union_areas)
best_ious = tf.reduce_max(iou_scores, axis=4)
conf_mask = conf_mask + tf.compat.v1.to_float(best_ious < 0.6) * (1 - y_true[..., 4]) * NO_OBJECT_SCALE
# penalize the confidence of the boxes, which are reponsible for corresponding ground truth box
conf_mask = conf_mask + y_true[..., 4] * OBJECT_SCALE
### class mask: simply the position of the ground truth boxes (the predictors)
class_mask = y_true[..., 4] * tf.gather(CLASS_WEIGHTS, true_box_class) * CLASS_SCALE
"""
Warm-up training
"""
no_boxes_mask = tf.compat.v1.to_float(coord_mask < COORD_SCALE/2.)
seen = tf.compat.v1.assign_add(seen, 1.)
true_box_xy, true_box_wh, coord_mask = tf.cond(tf.less(seen, WARM_UP_BATCHES),
lambda: [true_box_xy + (0.5 + cell_grid) * no_boxes_mask,
true_box_wh + tf.ones_like(true_box_wh) * np.reshape(ANCHORS, [1,1,1,BOX,2]) * no_boxes_mask,
tf.ones_like(coord_mask)],
lambda: [true_box_xy,
true_box_wh,
coord_mask])
"""
Finalize the loss
"""
nb_coord_box = tf.reduce_sum(tf.compat.v1.to_float(coord_mask > 0.0))
nb_conf_box = tf.reduce_sum(tf.compat.v1.to_float(conf_mask > 0.0))
nb_class_box = tf.reduce_sum(tf.compat.v1.to_float(class_mask > 0.0))
loss_xy = tf.reduce_sum(tf.square(true_box_xy-pred_box_xy) * coord_mask) / (nb_coord_box + 1e-6) / 2.
loss_wh = tf.reduce_sum(tf.square(true_box_wh-pred_box_wh) * coord_mask) / (nb_coord_box + 1e-6) / 2.
loss_conf = tf.reduce_sum(tf.square(true_box_conf-pred_box_conf) * conf_mask) / (nb_conf_box + 1e-6) / 2.
loss_class = tf.nn.sparse_softmax_cross_entropy_with_logits(labels=true_box_class, logits=pred_box_class)
loss_class = tf.reduce_sum(loss_class * class_mask) / (nb_class_box + 1e-6)
loss = loss_xy + loss_wh + loss_conf + loss_class
nb_true_box = tf.reduce_sum(y_true[..., 4])
nb_pred_box = tf.reduce_sum(tf.compat.v1.to_float(true_box_conf > 0.5) * tf.compat.v1.to_float(pred_box_conf > 0.3))
"""
Debugging code
"""
current_recall = nb_pred_box/(nb_true_box + 1e-6)
total_recall = tf.compat.v1.assign_add(total_recall, current_recall)
loss = tf.compat.v1.Print(loss, [tf.zeros((1))], message='Dummy Line \t', summarize=1000)
loss = tf.compat.v1.Print(loss, [loss_xy], message='Loss XY \t', summarize=1000)
loss = tf.compat.v1.Print(loss, [loss_wh], message='Loss WH \t', summarize=1000)
loss = tf.compat.v1.Print(loss, [loss_conf], message='Loss Conf \t', summarize=1000)
loss = tf.compat.v1.Print(loss, [loss_class], message='Loss Class \t', summarize=1000)
loss = tf.compat.v1.Print(loss, [loss], message='Total Loss \t', summarize=1000)
loss = tf.compat.v1.Print(loss, [current_recall], message='Current Recall \t', summarize=1000)
loss = tf.compat.v1.Print(loss, [total_recall/seen], message='Average Recall \t', summarize=1000)
return loss
For me Python crashes when I use this line:
from tensorflow.python.framework.ops import disable_eager_execution disable_eager_execution()
and this also doesn't help:
yolo_model.compile(loss=custom_loss, optimizer=optimizer, run_eagerly=False)
Using tensorflow.keras instead of keras also doesn't help unfortunately, did you do anything additionaly to those steps described?
The Error I get is also
TypeError: Cannot convert a symbolic Keras input/output to a numpy array. This error may indicate that you're trying to pass a symbolic value to a NumPy call, which is not supported. Or, you may be trying to pass Keras symbolic inputs/outputs to a TF API that does not register dispatching, preventing Keras from automatically converting the API call to a lambda layer in the Functional Model.